Related papers: MOVER: Mask, Over-generate and Rank for Hyperbole …

Headline generation is a special type of text summarization task. While the amount of available training data for this task is almost unlimited, it still remains challenging, as learning to generate headlines for news articles implies that…

Large language models often expose their brittleness in reasoning tasks, especially while executing long chains of reasoning over context. We propose MemReasoner, a new and simple memory-augmented LLM architecture, in which the memory…

Data scarcity and class imbalance are persistent challenges in training robust NLP models, especially in specialized domains or low-resource settings. We propose a novel technique, SMOTExT, that adapts the idea of Synthetic Minority…

Metaphor pervades everyday language, allowing speakers to express abstract concepts via concrete domains. While prior work has studied metaphors cognitively and psycholinguistically, large-scale comparisons with literal language remain…

Round-trip Machine Translation (MT) is a popular choice for paraphrase generation, which leverages readily available parallel corpora for supervision. In this paper, we formalize the implicit similarity function induced by this approach,…

While many BERT-based cross-modal pre-trained models produce excellent results on downstream understanding tasks like image-text retrieval and VQA, they cannot be applied to generation tasks directly. In this paper, we propose XGPT, a new…

Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language models (PLMs) need to be trained to encompass both the relevance matching task and the cross-language alignment task. However, cross-lingual data…

Large-scale models for learning fixed-dimensional cross-lingual sentence representations like LASER (Artetxe and Schwenk, 2019b) lead to significant improvement in performance on downstream tasks. However, further increases and…

Hyperproperties lift conventional trace-based languages from a set of execution traces to a set of sets of executions. From a formal-language perspective, these are sets of sets of words, namely hyperlanguages. Hyperautomata are based on…

We consider the task of inferring is-a relationships from large text corpora. For this purpose, we propose a new method combining hyperbolic embeddings and Hearst patterns. This approach allows us to set appropriate constraints for…

Data-to-text (D2T) generation is the task of generating texts from structured inputs. We observed that when the same target sentence was repeated twice, Transformer (T5) based model generates an output made up of asymmetric sentences from…

We discover a robust self-supervised strategy tailored towards molecular representations for generative masked language models through a series of tailored, in-depth ablations. Using this pre-training strategy, we train BARTSmiles, a…

Evaluating text generation capabilities of large language models (LLMs) is challenging, particularly for low-resource languages where methods for direct assessment are scarce. We propose MUG-Eval, a novel framework that evaluates LLMs'…

Reading comprehension is a crucial skill in many aspects of education, including language learning, cognitive development, and fostering early literacy skills in children. Automated answer-aware reading comprehension question generation has…

Large pretrained language models (PLMs) typically tokenize the input string into contiguous subwords before any pretraining or inference. However, previous studies have claimed that this form of subword tokenization is inadequate for…

Paraphrases are a vital tool to assist language understanding tasks such as question answering, style transfer, semantic parsing, and data augmentation tasks. Indic languages are complex in natural language processing (NLP) due to their…

Despite significant progress in text generation models, a serious limitation is their tendency to produce text that is factually inconsistent with information in the input. Recent work has studied whether textual entailment systems can be…

In this work, we introduce Speech-Copilot, a modular framework for instruction-oriented speech-processing tasks that minimizes human effort in toolset construction. Unlike end-to-end methods using large audio-language models, Speech-Copilot…

Hypergraph Lambek grammars (HL-grammars) is a novel logical approach to generating graph languages based on the hypergraph Lambek calculus. In this paper, we establish a precise relation between HL-grammars and hypergraph grammars based on…

Large language models augmented with task-relevant documents have demonstrated impressive performance on knowledge-intensive tasks. However, regarding how to obtain effective documents, the existing methods are mainly divided into two…