Related papers: Targeted Syntactic Evaluation of Language Models o…
Automating primary stress identification has been an active research field due to the role of stress in encoding meaning and aiding speech comprehension. Previous studies relied mainly on traditional acoustic features and English datasets.…
Targeted sentiment classification predicts the sentiment polarity on given target mentions in input texts. Dominant methods employ neural networks for encoding the input sentence and extracting relations between target mentions and their…
This discussion paper re-examines SemEval-2020 Task 1, the most influential shared benchmark for lexical semantic change detection, through a three-part evaluative framework: operationalisation, data quality, and benchmark design. First, at…
Machine learning techniques applied to the Natural Language Processing (NLP) component of conversational agent development show promising results for improved accuracy and quality of feedback that a conversational agent can provide. The…
Syntactic structures used to play a vital role in natural language processing (NLP), but since the deep learning revolution, NLP has been gradually dominated by neural models that do not consider syntactic structures in their design. One…
Structured language models for speech recognition have been shown to remedy the weaknesses of n-gram models. All current structured language models are, however, limited in that they do not take into account dependencies between…
We propose a generative model for a sentence that uses two latent variables, with one intended to represent the syntax of the sentence and the other to represent its semantics. We show we can achieve better disentanglement between semantic…
Transformer-based language models achieve high performance on various tasks, but we still lack understanding of the kind of linguistic knowledge they learn and rely on. We evaluate three models (BERT, RoBERTa, and ALBERT), testing their…
Language model pretraining generally targets a broad range of use cases and incorporates data from diverse sources. However, there are instances where we desire a model that excels in specific areas without markedly compromising performance…
Language models, especially transformer-based ones, have achieved colossal success in NLP. To be precise, studies like BERT for NLU and works like GPT-3 for NLG are very important. If we consider DNA sequences as a text written with an…
In translation, a concept represented by a single word in a source language can have multiple variations in a target language. The task of lexical selection requires using context to identify which variation is most appropriate for a source…
Distantly supervised relation extraction is widely used to extract relational facts from text, but suffers from noisy labels. Current relation extraction methods try to alleviate the noise by multi-instance learning and by providing…
In this study, we evaluated the performance of the state-of-the-art sequence tagging grammar error detection and correction model (SeqTagger) using Japanese university students' writing samples. With an automatic annotation toolkit, ERRANT,…
The schema-guided paradigm overcomes scalability issues inherent in building task-oriented dialogue (TOD) agents with static ontologies. Instead of operating on dialogue context alone, agents have access to hierarchical schemas containing…
While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs. In this paper, we introduce \textbf{G}enerative…
Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…
This paper evaluates global-scale dialect identification for 14 national varieties of English as a means for studying syntactic variation. The paper makes three main contributions: (i) introducing data-driven language mapping as a method…
Identification of cognates across related languages is one of the primary problems in historical linguistics. Automated cognate identification is helpful for several downstream tasks including identifying sound correspondences,…
This paper is devoted to the extraction of entities and semantic relations between them from scientific texts, where we consider scientific terms as entities. In this paper, we present a dataset that includes annotations for two tasks and…
This research proposes a novel approach to the Word Sense Disambiguation (WSD) task in the Georgian language, based on supervised fine-tuning of a pre-trained Large Language Model (LLM) on a dataset formed by filtering the Georgian Common…