Related papers: Collecting Diverse Natural Language Inference Prob…
Computing universal distributed representations of sentences is a fundamental task in natural language processing. We propose a method to learn such representations by encoding the suffixes of word sequences in a sentence and training on…
Natural Language Inference (NLI) focuses on ascertaining the logical relationship (entailment, contradiction, or neutral) between a given premise and hypothesis. This task presents significant challenges due to inherent linguistic features…
Natural language generation (NLG) is a critical component in a spoken dialogue system. This paper presents a Recurrent Neural Network based Encoder-Decoder architecture, in which an LSTM-based decoder is introduced to select, aggregate…
We propose a stochastic answer network (SAN) to explore multi-step inference strategies in Natural Language Inference. Rather than directly predicting the results given the inputs, the model maintains a state and iteratively refines its…
Metaphors are a ubiquitous but often overlooked part of everyday language. As a complex cognitive-linguistic phenomenon, they provide a valuable means to evaluate whether language models can capture deeper aspects of meaning, including…
Natural language inference (NLI) is critical for complex decision-making in biomedical domain. One key question, for example, is whether a given biomedical mechanism is supported by experimental evidence. This can be seen as an NLI problem…
We propose a general method to break down a main complex task into a set of intermediary easier sub-tasks, which are formulated in natural language as binary questions related to the final target task. Our method allows for representing…
Despite their linguistic competence, Large Language Models (LLMs) often struggle to reason reliably and flexibly. To identify these shortcomings, we introduce the Non-Linear Reasoning (NLR) dataset, a collection of 55 unique, hand-designed…
We create a new NLI test set that shows the deficiency of state-of-the-art models in inferences that require lexical and world knowledge. The new examples are simpler than the SNLI test set, containing sentences that differ by at most one…
We present a comprehensive work on automated veracity assessment from dataset creation to developing novel methods based on Natural Language Inference (NLI), focusing on misinformation related to the COVID-19 pandemic. We first describe the…
When evaluating an answer choice for Reading Comprehension task, other answer choices available for the question and the answers of related questions about the same paragraph often provide valuable information. In this paper, we propose a…
Ensuring complex systems meet regulations typically requires checking the validity of assurance cases through a claim-argument-evidence framework. Some challenges in this process include the complicated nature of legal and technical texts,…
The standard recurrent neural network language model (RNNLM) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an RNN-based variational autoencoder…
Word sense disambiguation is a fundamental challenge in natural language understanding. Current methods are primarily aimed at coarse-grained representations (e.g. WordNet synsets or FrameNet frames) and require hand-annotated training data…
Mathematical text is written using a combination of words and mathematical expressions. This combination, along with a specific way of structuring sentences makes it challenging for state-of-art NLP tools to understand and reason on top of…
Progress in natural language interfaces to databases (NLIDB) has been slow mainly due to linguistic issues (such as language ambiguity) and domain portability. Moreover, the lack of a large corpus to be used as a standard benchmark has made…
Text documents are structured on multiple levels of detail: individual words are related by syntax, but larger units of text are related by discourse structure. Existing language models generally fail to account for discourse structure, but…
Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process. However, biased datasets can also hurt the generalization…
While Natural Language Inference (NLI) models have achieved high performances on benchmark datasets, there are still concerns whether they truly capture the intended task, or largely exploit dataset artifacts. Through detailed analysis of…
Natural language understanding often requires deep semantic knowledge. Expanding on previous proposals, we suggest that some important aspects of semantic knowledge can be modeled as a language model if done at an appropriate level of…