Related papers: A Reactive Tabu Search Algorithm for Stimuli Gener…

Virtual assistants such as Google Assistant, Amazon Alexa, and Apple Siri enable users to interact with a large number of services and APIs on the web using natural language. In this work, we investigate two methods for Natural Language…

In this paper, we propose a simple, fast decoding algorithm that fosters diversity in neural generation. The algorithm modifies the standard beam search algorithm by adding an inter-sibling ranking penalty, favoring choosing hypotheses from…

Grammar competency estimation is essential for assessing linguistic proficiency in both written and spoken language; however, the spoken modality presents additional challenges due to its spontaneous, unstructured, and disfluent nature.…

Two well-known databases of semantic relationships between pairs of words used in psycholinguistics, feature-based and association-based, are studied as complex networks. We propose an algorithm to disentangle feature based relationships…

Topic modelling is a pivotal unsupervised machine learning technique for extracting valuable insights from large document collections. Existing neural topic modelling methods often encode contextual information of documents, while ignoring…

Automated story generation has been one of the long-standing challenges in NLP. Among all dimensions of stories, suspense is very common in human-written stories but relatively under-explored in AI-generated stories. While recent advances…

Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser -- which maps character-strings to subwords -- should not affect the…

Query expansion is a widely used technique to improve the recall of search systems. In this paper, we propose an approach to query expansion that leverages the generative abilities of Large Language Models (LLMs). Unlike traditional query…

Human infants acquire their verbal lexicon with minimal prior knowledge of language based on the statistical properties of phonological distributions and the co-occurrence of other sensory stimuli. This study proposes a novel fully…

Keyword spotting systems continuously process audio streams to detect keywords. One of the most challenging tasks in designing such systems is to reduce False Alarm (FA) which happens when the system falsely registers a keyword despite the…

Language models pretrained on text-only corpora often struggle with tasks that require auditory commonsense knowledge. Previous work addresses this problem by augmenting the language model to retrieve knowledge from external audio…

Recent studies have demonstrated that the ability of dense retrieval models to generalize to target domains with different distributions is limited, which contrasts with the results obtained with interaction-based models. Prior attempts to…

Large language models (LLMs) have demonstrated impressive performance in mathematical and commonsense reasoning tasks using chain-of-thought (CoT) prompting techniques. But can they perform emotional reasoning by concatenating `Let's think…

We propose a simple and effective re-ranking method for improving passage retrieval in open question answering. The re-ranker re-scores retrieved passages with a zero-shot question generation model, which uses a pre-trained language model…

Idioms are figurative expressions whose meanings often cannot be inferred from their individual words, making them difficult to process computationally and posing challenges for human experimental studies. This survey reviews datasets…

We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its…

Large Language Models (LLMs) can generate biased and toxic responses. Yet most prior work on LLM gender bias evaluation requires predefined gender-related phrases or gender stereotypes, which are challenging to be comprehensively collected…

Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language,…

Conventional statistics-based methods for joint Chinese word segmentation and part-of-speech tagging (S&T) have generalization ability to recognize new words that do not appear in the training data. An undesirable side effect is that a…

The retrieval augmented generation (RAG) system such as Retro has been shown to improve language modeling capabilities and reduce toxicity and hallucinations by retrieving from a database of non-parametric memory containing trillions of…