Search

To investigate the difference among patients, family members, physicians, and nurses in their ability to identify malnutrition risk in patients with thoracic cancer. The enrolled patients were evaluated by the NRS2002 nutritional risk scale. The patient-centered groups, including the patient, the primary caretaker, the physician, and the nurse, were given a questionnaire on their knowledge and understanding of nutrition therapy in cancer treatment. The incidence rate of nutritional risk in hospitalized patients with thoracic cancer was 13.8%. There were significant differences in the accuracy rate of nutritional risk assessment among the four groups (P 0.001), in which the nurses' was 70.3%, 55.1% for the physician, 38.7% for family members, and 33.0% for patients, which was the poorest accuracy rate. No significant correlation was found between the accuracy of nutritional risk assessment and the education level and personal monthly income of each population (P 0.05). Nearly all four groups considered it necessary to learn more about cancer nutrition therapy. For patients and their families, the main way to understand the knowledge of tumor nutrition was consultation with medical staff and information exchange between patients; for doctors, new media; and for nurses, classroom training. Nurses' assessment of nutritional risk in cancer patients achieved the highest accuracy, while the poorest accuracy originated from the patients.

Dissociated response (DR, reduction at baseline or increase

Background The NCCN (National Comprehensive Cancer Network) Clinical Practice Guidelines in Oncology (NCCN guidelines) recommend radical resection for T1-2N0M0 patients with limited-stage small cell lung cancer (LS-SCLC). However, only about 5% of patients with small cell cancer (SCLC) were initially diagnosed as T1-2N0M0. The purpose of our study was to analyze and compare the effects of the comprehensive treatment including radical surgery and concurrent chemoradiotherapy on the prognosis of patients with LS-SCLC. Methods We comprehensively reviewed the medical data of patients with SCLC diagnosed by pathology in our hospital from January 2011 to April 2018. The Ethics Committee of West China Hospital of Sichuan University approved the study. Finally, 50 patients with good follow-up and complete medical data were selected as the surgical group (S group). According to the clinical characteristics of the patients in the S group, 102 LS-SCLC patients who received concurrent chemoradiotherapy in the same period were included in the CCRT group (concurrent chemoradiotherapy group) as the control group. Then according to the orders of the adjuvant treatments, the patients in the S group were divided into the SA group (radical surgery + adjuvant chemotherapy + adjuvant radiotherapy group, 30 cases in total) and the NS group (neoadjuvant chemotherapy + radical surgery + adjuvant chemotherapy ± adjuvant radiotherapy group, 20 cases in total) for subgroup analysis. The SPSS 23.0 software was used for statistical analysis, and the t test was used for group comparison; Kaplan-Meier was used for survival analysis. P < 0.05 demonstrates a statistically significant difference. Results The median progress-free survival (PFS) in the S group (73 months) was significantly better than that in the CCRT group (10.5 months, P < 0.0001), and the median overall survival (OS) in the S group (79 months) was also significantly better than that in the CCRT group (23 months, P < 0.0001). Subgroup analysis showed that there was no significant difference between the NS group and the SA group. Conclusions For LS-SCLC patients, the comprehensive treatment including radical surgery (radical surgery + adjuvant chemotherapy ± adjuvant radiotherapy/neoadjuvant chemotherapy + radical surgery + adjuvant chemotherapy ± adjuvant radiotherapy)may be superior to concurrent chemoradiotherapy.

Knowledge graph embedding aims at modeling entities and relations with low-dimensional vectors. Most previous methods require that all entities should be seen during training, which is unpractical for real-world knowledge graphs with new entities emerging on a daily basis. Recent efforts on this issue suggest training a neighborhood aggregator in conjunction with the conventional entity and relation embeddings, which may help embed new entities inductively via their existing neighbors. However, their neighborhood aggregators neglect the unordered and unequal natures of an entity's neighbors. To this end, we summarize the desired properties that may lead to effective neighborhood aggregators. We also introduce a novel aggregator, namely, Logic Attention Network (LAN), which addresses the properties by aggregating neighbors with both rules- and network-based attention weights. By comparing with conventional aggregators on two knowledge graph completion tasks, we experimentally validate LAN's superiority in terms of the desired properties., Accepted by AAAI 2019

Collective entity disambiguation, or collective entity linking aims to jointly resolve multiple mentions by linking them to their associated entities in a knowledge base. Previous works are primarily based on the underlying assumption that entities within the same document are highly related. However, the extent to which these entities are actually connected in reality is rarely studied and therefore raises interesting research questions. For the first time, this paper shows that the semantic relationships between mentioned entities within a document are in fact less dense than expected. This could be attributed to several reasons such as noise, data sparsity, and knowledge base incompleteness. As a remedy, we introduce MINTREE, a new tree-based objective for the problem of entity disambiguation. The key intuition behind MINTREE is the concept of coherence relaxation which utilizes the weight of a minimum spanning tree to measure the coherence between entities. Based on this new objective, we design Pair-Linking, a novel iterative solution for the MINTREE optimization problem. The idea of Pair-Linking is simple: instead of considering all the given mentions, Pair-Linking iteratively selects a pair with the highest confidence at each step for decision making. Via extensive experiments on eight benchmark datasets, we show that our approach is not only more accurate but also surprisingly faster than many state-of-the-art collective linking algorithms MOE (Min. of Education, S’pore) Accepted version

Integrating extracted knowledge from the Web to knowledge graphs (KGs) can facilitate tasks like question answering. We study relation integration that aims to align free-text relations in subject-relation-object extractions to relations in a target KG. To address the challenge that free-text relations are ambiguous, previous methods exploit neighbor entities and relations for additional context. However, the predictions are made independently, which can be mutually inconsistent. We propose a two-stage Collective Relation Integration (CoRI) model, where the first stage independently makes candidate predictions, and the second stage employs a collective model that accesses all candidate predictions to make globally coherent predictions. We further improve the collective model with augmented data from the portion of the target KG that is otherwise unused. Experiment results on two datasets show that CoRI can significantly outperform the baselines, improving AUC from .677 to .748 and from .716 to .780, respectively., Comment: ACL 2021

We address hypernymy detection, i.e., whether an is-a relationship exists between words (x, y), with the help of large textual corpora. Most conventional approaches to this task have been categorized to be either pattern-based or distributional. Recent studies suggest that pattern-based ones are superior, if large-scale Hearst pairs are extracted and fed, with the sparsity of unseen (x, y) pairs relieved. However, they become invalid in some specific sparsity cases, where x or y is not involved in any pattern. For the first time, this paper quantifies the non-negligible existence of those specific cases. We also demonstrate that distributional methods are ideal to make up for pattern-based ones in such cases. We devise a complementary framework, under which a pattern-based and a distributional model collaborate seamlessly in cases which they each prefer. On several benchmark datasets, our framework achieves competitive improvements and the case study shows its better interpretability., Accepted by EMNLP2020 Main Conference

Existing studies have yet to elucidate clearly the mechanisms of secondary resistance to third generation epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKIs), neither is there any established standard therapy for patients resistant to third generation EGFR-TKIs. This case report demonstrates a rare mutation pattern in a male patient with a pathologic diagnosis of non-small cell lung cancer (NSCLC) harboring an EGFR exon 19 deletion (19Del) mutation, who then acquired an EGFR-T790M mutation after developing resistance to the first generation EGFR-TKI (gefitinib). The mutation reverted to the original EGFR-19Del mutation after the patient developed secondary resistance against the third generation TKI (osimertinib). This patient eventually achieved partial response (PR) with second generation TKI (afatinib) as a fourth-line treatment.

Next-location recommendation is an emerging task with the proliferation of location-based services. It is the task of recommending the next location to visit for a user, given her past check-in records. Although several principled solutions have been proposed for this task, existing studies have not well characterized the temporal factors in the recommendation. From three real-world datasets, our quantitative analysis reveals that temporal factors play an important role in next-location recommendation, including the periodical temporal preference and dynamic personal preference. In this paper, we propose a Time-Aware Trajectory Embedding Model (TA-TEM) to incorporate three kinds of temporal factors in next-location recommendation. Based on distributed representation learning, the proposed TA-TEM jointly models multiple kinds of temporal factors in a unified manner. TA-TEM also enhances the sequential context by using a longer context window. Experiments show that TA-TEM outperforms several competitive baselines.

Conditional Text Generation has drawn much attention as a topic of Natural Language Generation (NLG) which provides the possibility for humans to control the properties of generated contents. Current conditional generation models cannot handle emerging conditions due to their joint end-to-end learning fashion. When a new condition added, these techniques require full retraining. In this paper, we present a new framework named Pre-train and Plug-in Variational Auto-Encoder (PPVAE) towards flexible conditional text generation. PPVAE decouples the text generation module from the condition representation module to allow "one-to-many" conditional generation. When a fresh condition emerges, only a lightweight network needs to be trained and works as a plug-in for PPVAE, which is efficient and desirable for real-world applications. Extensive experiments demonstrate the superiority of PPVAE against the existing alternatives with better conditionality and diversity but less training effort., Accepted as a long paper at ACL 2020

Identifying the named entities mentioned in text would enrich many semantic applications at the downstream level. However, due to the predominant usage of colloquial language in microblogs, the named entity recognition (NER) in Chinese microblogs experience significant performance deterioration, compared with performing NER in formal Chinese corpus. In this paper, we propose a simple yet effective neural framework to derive the character-level embeddings for NER in Chinese text, named ME-CNER. A character embedding is derived with rich semantic information harnessed at multiple granularities, ranging from radical, character to word levels. The experimental results demonstrate that the proposed approach achieves a large performance improvement on Weibo dataset and comparable performance on MSRA news dataset with lower computational cost against the existing state-of-the-art alternatives., accepted at CIKM 2019

In this paper, we define and study a new task called Context-Aware Semantic Expansion (CASE). Given a seed term in a sentential context, we aim to suggest other terms that well fit the context as the seed. CASE has many interesting applications such as query suggestion, computer-assisted writing, and word sense disambiguation, to name a few. Previous explorations, if any, only involve some similar tasks, and all require human annotations for evaluation. In this study, we demonstrate that annotations for this task can be harvested at scale from existing corpora, in a fully automatic manner. On a dataset of 1.8 million sentences thus derived, we propose a network architecture that encodes the context and seed term separately before suggesting alternative terms. The context encoder in this architecture can be easily extended by incorporating seed-aware attention. Our experiments demonstrate that competitive results are achieved with appropriate choices of context encoder and attention scoring function., Comment: Accepted by AAAI 2020

Many domain-specific websites host a profile page for each entity (e.g., locations on Foursquare, movies on IMDb, and products on Amazon), and users can post comments on it. When commenting on an entity, users often mention other entities for reference or comparison. Compared with web pages and tweets, disambiguating the mentioned entities in user comments has not received much attention. This paper investigates linking fine-grained locations in Foursquare comments. We demonstrate that the focal location, i.e., the location that a comment is posted on, provides rich contexts for linking. To exploit such information, we represent the Foursquare data in a graph, which includes locations, comments, and their relations. A probabilistic model named FocalLink is proposed to estimate the probability that a user mentions a location when commenting on a focal location, by following different kinds of relations. Experimental results show that FocalLink is consistently superior to different baselines.

With the development of medical information management, numerous medical data are being classified, indexed, and searched in various systems. Disease phrase matching, i.e., deciding whether two given disease phrases interpret each other, is a basic but crucial preprocessing step for the above tasks. Being capable of relieving the scarceness of annotations, domain adaptation is generally considered useful in medical systems. However, efforts on applying it to phrase matching remain limited. This paper presents a domain-adaptive matching network for disease phrases. Our network achieves domain adaptation by adversarial training, i.e., preferring features indicating whether the two phrases match, rather than which domain they come from. Experiments suggest that our model has the best performance among the very few non-adaptive or adaptive methods that can benefit from out-of-domain annotations.

Twitter provides us a convenient channel to get access to the immediate information about major events. However, it is challenging to acquire a clean and complete set of event-related data due to the characteristics of tweets, eg short and noisy. In this paper, we propose a semi-supervised method to obtain high quality event-related tweets from Twitter stream, in terms of precision and recall. Specifically, candidate event-related tweets are selected based on a set of keywords. We propose to generate and update these keywords dynamically along the event development. To be included in this keyword set, words are evaluated based on single word properties, property based on co-occurred words, and changes of word importance over time. Our solution is capable of capturing keywords of emerging aspects or aspects with increasing importance along event evolvement. By leveraging keyword importance information and a few labeled tweets, we propose a semi-supervised expectation maximization process to identify event-related tweets. This process significantly reduces human effort in acquiring high quality tweets. Experiments on three real world datasets show that our solution outperforms state-of-the-art approaches by up to 10% in F1 measure.

Many domain-specific websites host a profile page for each entity (e.g., locations on Foursquare, movies on IMDb, and products on Amazon) for users to post comments on. When commenting on an entity, users often mention other entities for reference or comparison. Compared with web pages and tweets, the problem of disambiguating the mentioned entities in user comments has not received much attention. This paper investigates linking fine-grained locations in Foursquare comments. We demonstrate that the focal location, i.e., the location that a comment is posted on, provides rich contexts for the linking task. To exploit such information, we represent the Foursquare data in a graph, which includes locations, comments, and their relations. A probabilistic model named FocalLink is proposed to estimate the probability that a user mentions a location when commenting on a focal location, by following different kinds of relations. Experimental results show that FocalLink is consistently superior under different collective linking settings. MOE (Min. of Education, S’pore) Accepted version

This study aims to investigate the effect of hematoporphyrin monomethyl ether (HMME)-mediated sonodynamic antimicrobial chemotherapy (SACT) on Staphylococcus aureus. SACT was carried out using HMME and 1 MHz ultrasound irradiation. The bactericidal effect was evaluated by the counting colony-forming units (CFU), and important SACT parameters including ultrasound intensity and HMME concentration were determined. More than 95% of the bacteria colonies were effectively killed in the SACT group by 50 μg mL(-1) HMME combined with 6 W cm(-2) tone-burst ultrasound at 1 MHz, but this ultrasound level without HMME only reduced CFU by 38%. In the sonodynamic treatment, higher HMME concentrations and higher ultrasound intensities caused more death of bacteria. Incubation with different HMME concentrations without ultrasound showed no effect. Our results show that the HMME-mediated SACT can be significantly in killing S. aureus.

Knowledge bases have shown their effectiveness in facilitating services like Web search and question-answering. Nevertheless, it remains challenging for ordinary users to fully understand the structure of a knowledge base and to issue structural queries. In many cases, users may have a natural language question and also know some popular (but not all) entities as sample answers. In this paper, we study the Reverse top-k Neighborhood Pattern Query problem, with the aim of discovering structural queries of the question based on: (i) the structure of the knowledge base, and (ii) the sample answers of the question. The proposed solution contains two phases: filter and refine. In the filter phase, a search space of candidate queries is systematically explored. The invalid queries whose result sets do not fully cover the sample answers are filtered out. In the refine phase, all surviving queries are verified to ensure that they are sufficiently relevant to the sample answers, with the assumption that the sample answers are more well-known or popular than other entities in the results of relevant queries. Several optimization techniques are proposed to accelerate the refine phrase. For evaluation, we conduct extensive experiments using the DBpedia knowledge base and a set of real-life questions. Empirical results show that our algorithm is able to provide a small set of possible queries, which contains the query matching the user question in natural language.

Many users casually reveal their locations such as restaurants, landmarks, and shops in their tweets. Recognizing such fine-grained locations from tweets and then linking the location mentions to well-defined location profiles (e.g., with formal name, detailed address, and geo-coordinates etc.) offer a tremendous opportunity for many applications. Different from existing solutions which perform location recognition and linking as two sub-tasks sequentially in a pipeline setting, in this paper, we propose a novel joint framework to perform location recognition and location linking simultaneously in a joint search space. We formulate this end-to-end location linking problem as a structured prediction problem and propose a beam-search based algorithm. Based on the concept of multi-view learning, we further enable the algorithm to learn from unlabeled data to alleviate the dearth of labeled data. Extensive experiments are conducted to recognize locations mentioned in tweets and link them to location profiles in Foursquare. Experimental results show that the proposed joint learning algorithm outperforms the state-of-the-art solutions, and learning from unlabeled data improves both the recognition and linking accuracy.

Studies investigating the association between cytochrome P450 1B1 (CYP1B1) Asn453Ser (453 A/G, rs1800440) polymorphism and colorectal cancer (CRC) risk report conflicting results. The aim of this study was to quantitatively summarize the evidence for such a relationship. Two investigators independently searched the Medline and Embase Databases. Summary odds ratios (ORs) and 95% confidence intervals (95% CIs) for CYP1B1 polymorphism and CRC were calculated in a fixed-effects model (the Mantel–Haenszel method) and a random-effects model (the DerSimonian and Laird method) when appropriate. The pooled ORs were performed for co-dominant model (GG vs AA, GA vs AA), dominant model (GG + GA vs AA), and recessive model (GG vs GA + AA). This meta-analysis included 7 case-control studies, which included 6375 CRC cases and 7003 controls. Overall, the variant genotypes (GG and GA) of the 453 A/G were not associated with CRC risk when compared with the wild-type AA homozygote (GG vs AA, OR = 0.94, 95% CI = 0.77–1.14; GA vs AA, OR = 0.99, 95% CI = 0.87–1.12). Similarly, no associations were found in the dominant and recessive models (dominant model, OR = 0.98, 95% CI = 0.87–1.09; recessive model, OR = 0.94, 95% CI = 0.77–1.14). When stratifying for country, study sample size, matched control and source of controls, no evidence of significant association was observed in any subgroup, except among those studies from “Canada”. No publication bias was found in the present study. No association was found between the CYP1B1 Asn453Ser polymorphism and risk of CRC among Caucasians.

The authors of "A Survey of Location Prediction on Twitter" which appeared in the September 2018 issue of this journal would like to point out a typo that occurred in the first footnote on page 1. Xin Zheng was mistakenly listed as the corresponding author. The correct corresponding author is Jialong Han. Please address any correspondence about this paper to him.