Related papers: Stretching Sentence-pair NLI Models to Reason over…
With the rapid development in Transformer-based language models, the reading comprehension tasks on short documents and simple questions have been largely addressed. Long documents, specifically the scientific documents that are densely…
Native Language Identification (NLI) - the task of identifying the native language (L1) of a person based on their writing in the second language (L2) - has applications in forensics, marketing, and second language acquisition.…
Despite the impressive capability of large language models (LLMs), knowing when to trust their generations remains an open challenge. The recent literature on uncertainty quantification of natural language generation (NLG) utilises a…
Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to…
With the development and proliferation of large, complex, black-box models for solving many natural language processing (NLP) tasks, there is also an increasing necessity of methods to stress-test these models and provide some degree of…
Document alignment aims to identify pairs of documents in two distinct languages that are of comparable content or translations of each other. Such aligned data can be used for a variety of NLP tasks from training cross-lingual…
Machine learning models can reach high performance on benchmark natural language processing (NLP) datasets but fail in more challenging settings. We study this issue when a pre-trained model learns dataset artifacts in natural language…
In the field of information retrieval, Query Likelihood Models (QLMs) rank documents based on the probability of generating the query given the content of a document. Recently, advanced large language models (LLMs) have emerged as effective…
We apply the Adversarial NLI dataset to train the NLI model and show that the model has the potential to enhance factual correctness in abstract summarization. We follow the work of Falke et al. (2019), which rank multiple generated…
Generating diverse, interesting responses to chitchat conversations is a problem for neural conversational agents. This paper makes two substantial contributions to improving diversity in dialogue generation. First, we propose a novel…
Recent studies have demonstrated the great potential of Large Language Models (LLMs) serving as zero-shot relevance rankers. The typical approach involves making comparisons between pairs or lists of documents. Although effective, these…
This article analyzes the use of Large Language Models (LLMs) as support for the conceptual modeling of relational databases through the automatic generation of Entity-Relationship (ER) diagrams from natural language requirements. The…
Semantic sentence embeddings are usually supervisedly built minimizing distances between pairs of embeddings of sentences labelled as semantically similar by annotators. Since big labelled datasets are rare, in particular for non-English…
Combining a pretrained language model (PLM) with textual patterns has been shown to help in both zero- and few-shot settings. For zero-shot performance, it makes sense to design patterns that closely resemble the text seen during…
The degree of semantic relatedness of two units of language has long been considered fundamental to understanding meaning. Additionally, automatically determining relatedness has many applications such as question answering and…
In NLP, zero-shot classification (ZSC) is the task of assigning labels to textual data without any labeled examples for the target classes. A common method for ZSC is to fine-tune a language model on a Natural Language Inference (NLI)…
In today's day and age where information is rapidly spread through online platforms, the rise of fake news poses an alarming threat to the integrity of public discourse, societal trust, and reputed news sources. Classical machine learning…
We propose SETI (Systematicity Evaluation of Textual Inference), a novel and comprehensive benchmark designed for evaluating pre-trained language models (PLMs) for their systematicity capabilities in the domain of textual inference.…
How can we interpret and retrieve medical evidence to support clinical decisions? Clinical trial reports (CTR) amassed over the years contain indispensable information for the development of personalized medicine. However, it is practically…
Natural Language Inference (NLI) models frequently rely on spurious correlations rather than semantic reasoning. Existing mitigation strategies often incur high annotation costs or trigger catastrophic forgetting during fine-tuning. We…