Related papers: Exploiting Diversity in Natural Language Processin…

We introduce a novel approach to incorporate syntax into natural language inference (NLI) models. Our method uses contextual token-level vector representations from a pretrained dependency parser. Like other contextual embedders, our method…

Transformer has been successfully applied to many natural language processing tasks. However, for textual sequence matching, simple matching between the representation of a pair of sequences might bring in unnecessary noise. In this paper,…

We explore whether it is possible to build lighter parsers, that are statistically equivalent to their corresponding standard version, for a wide set of languages showing different structures and morphologies. As testbed, we use the…

The thesis presents an attempt at using the syntactic structure in natural language for improved language models for speech recognition. The structured language model merges techniques in automatic parsing and language modeling using an…

Recent advancements in generative large language models (LLMs) have significantly boosted the performance in natural language processing tasks. However, their efficiency is hampered by the inherent limitations in autoregressive token…

This paper proposes a novel technique that applies case-based reasoning in order to generate templates for reusable parse tree fragments, based on PoS tags of bigrams and trigrams that demonstrate low variability in their syntactic analyses…

Although the Transformer is currently the best-performing architecture in the homogeneous configuration (self-attention only) in Neural Machine Translation, many State-of-the-Art models in Natural Language Processing are made of a…

Integrating the outputs of multiple classifiers via combiners or meta-learners has led to substantial improvements in several difficult pattern recognition problems. In the typical setting investigated till now, each classifier is trained…

Sequence tagging models for constituent parsing are faster, but less accurate than other types of parsers. In this work, we address the following weaknesses of such constituent parsers: (a) high error rates around closing brackets of long…

Measuring what linguistic information is encoded in neural models of language has become popular in NLP. Researchers approach this enterprise by training "probes" - supervised models designed to extract linguistic structure from another…

Ensemble methods using multiple classifiers have proven to be the most successful approach for the task of Native Language Identification (NLI), achieving the current state of the art. However, a systematic examination of ensemble methods…

Many natural language processing (NLP) tasks involve reasoning with textual spans, including question answering, entity recognition, and coreference resolution. While extensive research has focused on functional architectures for…

Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we provide the simple…

The success of many natural language processing (NLP) tasks is bound by the number and quality of annotated data, but there is often a shortage of such training data. In this paper, we ask the question: "Can we combine a neural network (NN)…

With recent advancements in large language models, methods like chain-of-thought prompting to elicit reasoning chains have been shown to improve results on reasoning tasks. However, tasks that require multiple steps of reasoning still pose…

Collaborative competitions have gained popularity in the scientific and technological fields. These competitions involve defining tasks, selecting evaluation scores, and devising result verification methods. In the standard scenario,…

Probing classifiers have emerged as one of the prominent methodologies for interpreting and analyzing deep neural network models of natural language processing. The basic idea is simple -- a classifier is trained to predict some linguistic…

Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…

Modern language models leverage increasingly large numbers of parameters to achieve performance on natural language understanding tasks. Ensembling these models in specific configurations for downstream tasks show even further performance…

This paper explores the task of leveraging typology in the context of cross-lingual dependency parsing. While this linguistic information has shown great promise in pre-neural parsing, results for neural architectures have been mixed. The…