Search

Textual representations play an important role in the field of natural language processing (NLP). The efficiency of NLP tasks, such as text comprehension and information extraction, can be significantly improved with proper textual representations. As neural networks are gradually applied to learn the representation of words and phrases, fairly efficient models of learning short text representations have been developed, such as the continuous bag of words (CBOW) and skip-gram models, and they have been extensively employed in a variety of NLP tasks. Because of the complex structure generated by the longer text lengths, such as sentences, algorithms appropriate for learning short textual representations are not applicable for learning long textual representations. One method of learning long textual representations is the Long Short-Term Memory (LSTM) network, which is suitable for processing sequences. However, the standard LSTM does not adequately address the primary sentence structure (subject, predicate and object), which is an important factor for producing appropriate sentence representations. To resolve this issue, this paper proposes the dependency-based LSTM model (D-LSTM). The D-LSTM divides a sentence representation into two parts: a basic component and a supporting component. The D-LSTM uses a pre-trained dependency parser to obtain the primary sentence information and generate supporting components, and it also uses a standard LSTM model to generate the basic sentence components. A weight factor that can adjust the ratio of the basic and supporting components in a sentence is introduced to generate the sentence representation. Compared with the representation learned by the standard LSTM, the sentence representation learned by the D-LSTM contains a greater amount of useful information. The experimental results show that the D-LSTM is superior to the standard LSTM for sentences involving compositional knowledge (SICK) data.

Text representation can map text into a vector space for subsequent use in numerical calculations and processing tasks. Word embedding is an important component of text representation. Most existing word embedding models focus on writing and utilize context, weight, dependency, morphology, etc., to optimize the training. However, from the linguistic point of view, spoken language is a more direct expression of semantics; writing has meaning only as a recording of spoken language. Therefore, this paper proposes the concept of a pronunciation-enhanced word embedding model (PWE) that integrates speech information into training to fully apply the roles of both speech and writing to meaning. This paper uses the Chinese language, English language and Spanish language as examples and presents several models that integrate word pronunciation characteristics into word embedding. Word similarity and text classification experiments show that the PWE outperforms the baseline model that does not include speech information. Language is a storehouse of sound-images; therefore, the PWE can be applied to most languages.

Acute febrile infections have historically been used to treat cancer. To explore the underlying mechanism, we studied chronic effects of fever on cancer cell growth and chemotherapeutic efficacy in cell culture. We found that culturing cancer cells at 39°C mildly inhibited cell growth by arresting the cells at the G1 phase of the cell cycle. When cells were seeded in culture dishes at a lower density, e.g. about 1000-2000 cells per 35-mm dish, the growth inhibition was much greater, manifested as many fewer cell colonies in the 39°C dishes, compared with the results at a higher density seeding, e.g. 20,000 cells per dish, suggesting that cell-cell collaboration as the Allee effect in cell culture is inhibited at 39°C. Withdrawal of cells from serum enhanced the G1 arrest at 39°C and, for some cell lines such as A549 lung cancer cells, serum replenishment failed to quickly drive the cells from the G1 into the S and G2-M phases. Therapeutic effects of several chemotherapeutic agents, including clove bud extracts, on several cancer cell lines were more potent at 39°C than at 37°C, especially when the cells were seeded at a low density. For some cell lines and some agents, this enhancement is long-lasting, i.e. continuing after the cessation of the treatment. Collectively these results suggest that hyperthermia may inhibit cancer cell growth by G1 arrest and by inhibition of cell-cell collaboration, and may enhance the efficacy of several chemotherapeutic agents, an effect which may persist beyond the termination of chemotherapy.