Search

To find answers for subjective questions about many topics through Q\&A forums, questioners and answerers can cooperatively help themselves by sharing their doubts or answers based on their background and life experiences. These experiences can help machines redirect questioners to find better answers based on community question-answering models. This work proposes a comparative analysis of the pairwise community answer retrieval models in the home improvement domain considering different kinds of user question context information. Community Question-Answering (CQA) models must rank candidate answers in decreasing order of relevance for a user question. Our contribution consists of transformer-based language models using different kinds of user information to accurate the model generalisation. To train our model, we propose a proper CQA dataset in the home improvement domain that consists of information extracted from community forums, including question context information. We evaluate our approach by comparing the performance of each baseline model based on rank-aware evaluation measures.

Multi-Label Text Classification (MLTC) is a well-known NLP task that allows the classification of texts into multiple categories indicating their most relevant domains. However, training model tasks on texts from web user deal with redundancy or ambiguity of linguistic information. In this work, we propose a comparative study about different neural network models for a multi-label text categorisation task in finance domain. Our main contribution consists of presenting a new annotated dataset that contains ∼26k posts from users associated to finance categories. To build that dataset, we defined 10 specific-domain categories that cover financial texts. To serve as a baseline, we present a comparative study analysing both the performance and training time of different learning models for the task of multilabel text categorisation on the new dataset. The results show that transformer-based language models outperformed RNN-based neural networks in all scenarios in terms of precision. However, transformers took much more time than RNN models to train an epoch model.

Patent, a form of intellectual property often be in the first place when it comes to securing an invention. The legal boundaries created then will become key stages of turning an invention into a commercial product. In recent years, the unprecedented growth of patent applications has induced a great challenge to patent examiners. Novelty detection is one major step considered before and after filing a patent application to assure claimed inventions are new and non-obvious. This itself is considered as a salient stage of prior art search by patent applicants, patent examiners, patent attorneys, patent agent professionals. Management in terms of critical analysis of such a large scale of documents has become a challenge since missing an optimal, effective, and efficient system. To this end, we come up with a novel experimental case study to foster highly recursive and interactive tasks. We developed and investigated more than 50 machine learning models on the considered dataset. The contributions of this work include: (1) outlined and anticipated the importance of novelty detection in the patent domain, (2) develop various baseline models for novelty detection, (3) utilize immense contributions of deep learning towards NLP to improve baseline models, (4) assess the performance of every model by using different word embeddings like word2vec, glove, fasttext, and domain-specific embeddings, (5) a novel application of NBSVM algorithm on our dataset, and considered as exceptionally good of our models. We articulated the fulfillment of models using training and validation curves to prove seemingly negligible overfit or no overfit, in the hope that effective automation in novelty detection helps in driving down the routine prior art search efforts.

PreferenceSQL is an SQL extension for standard relational databases supporting soft constraints and is used to find relevant data intuitively. Meanwhile, the Semantic Web has interoperability advantages and helps to retrieve information with machine-readable data. We use the benefits of both technologies by combining preferences from SQL with SPARQL, the query language of the Semantic Web. This work provides implementation details in Apache Jena for the new composite called 'PreferenceSPARQL'. Furthermore, we contribute comprehensive benchmarks that show which preference algorithm is best suited for our approach.