Related papers: A Mention-Ranking Model for Abstract Anaphora Reso…

Large language models (LLMs) suffer from forgetting of upstream knowledge when fine-tuned. Despite efforts on mitigating forgetting, few have investigated how forgotten upstream examples are dependent on newly learned tasks. Insights on…

Learning the past tense of English verbs - a seemingly minor aspect of language acquisition - has generated heated debates since 1986, and has become a landmark task for testing the adequacy of cognitive modeling. Several artificial neural…

Modeling the structure of coherent texts is a key NLP problem. The task of coherently organizing a given set of sentences has been commonly used to build and evaluate models that understand such structure. We propose an end-to-end…

Deep neural networks have achieved great successes on the image captioning task. However, most of the existing models depend heavily on paired image-sentence datasets, which are very expensive to acquire. In this paper, we make the first…

Text-to-image (T2I) models have achieved remarkable progress in high-quality image synthesis, yet most benchmarks rely on simple, self-contained prompts, failing to capture the complexity of real-world captions. Human-written captions often…

Sequential word order is important when processing text. Currently, neural networks (NNs) address this by modeling word position using position embeddings. The problem is that position embeddings capture the position of individual words,…

This paper investigates the impact of word-based RNN language models (RNN-LMs) on the performance of end-to-end automatic speech recognition (ASR). In our prior work, we have proposed a multi-level LM, in which character-based and…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Comparison and evaluation of graph-based representations of sentence meaning is a challenge because competing representations of the same sentence may have different number of nodes, and it is not obvious which nodes should be compared to…

Traditionally, natural language processing (NLP) models often use a rich set of features created by linguistic expertise, such as semantic representations. However, in the era of large language models (LLMs), more and more tasks are turned…

Most work in relation extraction forms a prediction by looking at a short span of text within a single sentence containing a single entity pair mention. This approach often does not consider interactions across mentions, requires redundant…

In the context of human-in-the-loop Machine Learning applications, like Decision Support Systems, interpretability approaches should provide actionable insights without making the users wait. In this paper, we propose Accelerated…

Neural language models encode rich knowledge about entities and their relationships which can be extracted from their representations using probing. Common properties of nouns (e.g., red strawberries, small ant) are, however, more…

Verbal omissions are complex syntactic phenomena in VP coordination structures. They occur when verbs and (some of) their arguments are omitted from subsequent clauses after being explicitly stated in an initial clause. Recovering these…

Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with…

Abstractive text summarization aims at compressing the information of a long source document into a rephrased, condensed summary. Despite advances in modeling techniques, abstractive summarization models still suffer from several key…

The Abstraction and Reasoning Corpus (ARC) poses a significant challenge to artificial intelligence, demanding broad generalization and few-shot learning capabilities that remain elusive for current deep learning methods, including large…

Automatic Speech Recognition (ASR) has witnessed a profound research interest. Recent breakthroughs have given ASR systems different prospects such as faithfully transcribing spoken language, which is a pivotal advancement in building…

One noticeable trend in metaphor detection is the embrace of linguistic theories such as the metaphor identification procedure (MIP) for model architecture design. While MIP clearly defines that the metaphoricity of a lexical unit is…

In multi-user semantic communication, language mismatche poses a significant challenge when independently trained agents interact. We present a novel semantic equalization algorithm that enables communication between agents with different…