相关论文: Joint Learning of Context and Feedback Embeddings …

Backchannels (e.g., `yeah', `mhm', and `right') are short, non-interruptive feedback signals whose lexical form and prosody jointly convey pragmatic meaning. While prior computational research has largely focused on predicting backchannel…

Embedding models, which learn latent representations of users and items based on user-item interaction patterns, are a key component of recommendation systems. In many applications, contextual constraints need to be applied to refine…

The use of conversational assistants to search for information is becoming increasingly more popular among the general public, pushing the research towards more advanced and sophisticated techniques. In the last few years, in particular,…

Language models are often used as the backbone of modern dialogue systems. These models are pre-trained on large amounts of written fluent language. Repetition is typically penalised when evaluating language model generations. However, it…

Embeddings play an important role in end-to-end solutions for multi-modal language processing problems. Although there has been some effort to understand the properties of single-modality embedding spaces, particularly that of text, their…

Embedding-based approaches for dialog response retrieval embed the context-response pairs as points in the embedding space. These approaches are scalable, but fail to account for the complex, many-to-many relationships that exist between…

We present our latest findings on backchannel modeling novelly motivated by the canonical use of the minimal responses Yeah and Uh-huh in English and their correspondent tokens in German, and the effect of encoding the speaker-listener…

Human conversations contain many types of information, e.g., knowledge, common sense, and language habits. In this paper, we propose a conversational word embedding method named PR-Embedding, which utilizes the conversation pairs $…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

Contextualized word embedding models, such as ELMo, generate meaningful representations of words and their context. These models have been shown to have a great impact on downstream applications. However, in many cases, the contextualized…

We propose an architecture to jointly learn word and label embeddings for slot filling in spoken language understanding. The proposed approach encodes labels using a combination of word embeddings and straightforward word-label association…

Dialog response ranking is used to rank response candidates by considering their relation to the dialog history. Although researchers have addressed this concept for open-domain dialogs, little attention has been focused on task-oriented…

The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word…

Position embeddings, encoding the positional relationships among tokens in text sequences, make great contributions to modeling local context features in Transformer-based pre-trained language models. However, in Extractive Question…

Existing approaches to mapping-based cross-lingual word embeddings are based on the assumption that the source and target embedding spaces are structurally similar. The structures of embedding spaces largely depend on the co-occurrence…

Most human interactions occur in the form of spoken conversations where the semantic meaning of a given utterance depends on the context. Each utterance in spoken conversation can be represented by many semantic and speaker attributes, and…

Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. These tasks are formulated as a binary classification of responses given in a dialogue context, and models generally learn to make…

Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker. While recent large language models show remarkable…

We consider the problem of Recognizing Textual Entailment within an Information Retrieval context, where we must simultaneously determine the relevancy as well as degree of entailment for individual pieces of evidence to determine a yes/no…

Despite advances in open-domain dialogue systems, automatic evaluation of such systems is still a challenging problem. Traditional reference-based metrics such as BLEU are ineffective because there could be many valid responses for a given…