Related papers: Identifying a Circuit for Verb Conjugation in GPT-…

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the…

Large language models such as GPT-3 (Brown et al., 2020) can perform arbitrary tasks without undergoing fine-tuning after being prompted with only a few labeled examples. An arbitrary task can be reformulated as a natural language prompt,…

This study investigates how Large Language Models (LLMs), particularly BERT (Devlin et al., 2019) and GPT-2 (Radford et al., 2019), engage in pragmatic inference of scalar implicature, such as some. Two sets of experiments were conducted…

Long chain-of-thought (CoT) prompting helps Large Language Models (LLMs) solve difficult problems, but very long traces often slow or even degrade performance on fast, intuitive "System-1" tasks. We introduce Connector-Aware Compact CoT…

This research investigates the use of customized GPT models to enhance prompting proficiency among architecture students when generating AI-driven images. Prompt engineering is increasingly essential in architectural education due to the…

It has been reported that clustering-based topic models, which cluster high-quality sentence embeddings with an appropriate word selection method, can generate better topics than generative probabilistic topic models. However, these…

LSTM-based recurrent neural networks are the state-of-the-art for many natural language processing (NLP) tasks. Despite their performance, it is unclear whether, or how, LSTMs learn structural features of natural languages such as…

In practical settings, a speaker recognition system needs to identify a speaker given a short utterance, while the enrollment utterance may be relatively long. However, existing speaker recognition models perform poorly with such short…

Language models can be prompted to perform a wide variety of zero- and few-shot learning problems. However, performance varies significantly with the choice of prompt, and we do not yet understand why this happens or how to pick the best…

It is often the case that the best performing language model is an ensemble of a neural language model with n-grams. In this work, we propose a method to improve how these two models are combined. By using a small network which predicts the…

Accounts of human language processing have long appealed to implicit ``situation models'' that enrich comprehension with relevant but unstated world knowledge. Here, we apply causal intervention techniques to recent transformer models to…

With the advent of conversational assistants, like Amazon Alexa, Google Now, etc., dialogue systems are gaining a lot of traction, especially in industrial setting. These systems typically consist of Spoken Language understanding component…

In human conversations, ellipsis and coreference are commonly occurring linguistic phenomena. Although these phenomena are a mean of making human-machine conversations more fluent and natural, only few dialogue corpora contain explicit…

Grammatical Error Correction (GEC) is a task of detecting and correcting grammatical errors in sentences. Recently, neural machine translation systems have become popular approaches for this task. However, these methods lack the use of…

This study investigates the use of prompt engineering to enhance large language models (LLMs), specifically GPT-4o-mini and gemini-1.5-flash, in sentiment analysis tasks. It evaluates advanced prompting techniques like few-shot learning,…

Noun compound interpretation is the task of expressing a noun compound (e.g. chocolate bunny) in a free-text paraphrase that makes the relationship between the constituent nouns explicit (e.g. bunny-shaped chocolate). We propose…

We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge…

Grammatical error correction can be viewed as a low-resource sequence-to-sequence task, because publicly available parallel corpora are limited. To tackle this challenge, we first generate erroneous versions of large unannotated corpora…

Grammatical error correction tools are effective at correcting grammatical errors in users' input sentences but do not provide users with \textit{natural language} explanations about their errors. Such explanations are essential for helping…

Transformer-based pre-trained language models such as BERT have achieved remarkable results in Semantic Sentence Matching. However, existing models still suffer from insufficient ability to capture subtle differences. Minor noise like word…