Phrase

About: Phrase is a research topic. Over the lifetime, 12580 publications have been published within this topic receiving 317823 citations. The topic is also known as: syntagma & phrases.

Lattice-Based Search for Spoken Utterance Retrieval

Abstract: Recent work on spoken document retrieval has suggested that it is adequate to take the singlebest output of ASR, and perform text retrieval on this output. This is reasonable enough for the task of retrieving broadcast news stories, where word error rates are relatively low, and the stories are long enough to contain much redundancy. But it is patently not reasonable if one’s task is to retrieve a short snippet of speech in a domain where WER’s can be as high as 50%; such would be the situation with teleconference speech, where one’s task is to find if and when a participant uttered a certain phrase. In this paper we propose an indexing procedure for spoken utterance retrieval that works on lattices rather than just single-best text. We demonstrate that this procedure can improve F scores by over five points compared to singlebest retrieval on tasks with poor WER and low redundancy. The representation is flexible so that we can represent both word lattices, as well as phone lattices, the latter being important for improving performance when searching for phrases containing OOV words.

Semantic co-occurrence filtering for speech recognition and signal transcription applications

Abstract: A system and method for automatically transcribing an input question from a form convenient for user input into a form suitable for use by a computer. The question is a sequence of words represented in a form convenient for the user, such as a spoken utterance or a handwritten phrase. The question is transduced into a signal that is converted into a sequence of symbols. A set of hypotheses is generated from the sequence of symbols. The hypotheses are sequences of words represented in a form suitable for use by the computer, such as text. One or more information retrieval queries are constructed and executed to retrieve documents from a corpus (database). Retrieved documents are analyzed to produce an evaluation of the hypotheses of the set and to select one or more preferred hypotheses from the set. The preferred hypotheses are output to a display, speech synthesizer, or applications program. Additionally, retrieved documents relevant to the preferred hypotheses can be selected and output.

From Paraphrase Database to Compositional Paraphrase Model and Back

Abstract: The Paraphrase Database (PPDB; Ganitkevitch et al., 2013) is an extensive semantic resource, consisting of a list of phrase pairs with (heuristic) confidence estimates. However, it is still unclear how it can best be used, due to the heuristic nature of the confidences and its necessarily incomplete coverage. We propose models to leverage the phrase pairs from the PPDB to build parametric paraphrase models that score paraphrase pairs more accurately than the PPDB’s internal scores while simultaneously improving its coverage. They allow for learning phrase embeddings as well as improved word embeddings. Moreover, we introduce two new, manually annotated datasets to evaluate short-phrase paraphrasing models. Using our paraphrase model trained using PPDB, we achieve state-of-the-art results on standard word and bigram similarity tasks and beat strong baselines on our new short phrase paraphrase tasks.

An effective approach to document retrieval via utilizing WordNet and recognizing phrases

Abstract: Noun phrases in queries are identified and classified into four types: proper names, dictionary phrases, simple phrases and complex phrases. A document has a phrase if all content words in the phrase are within a window of a certain size. The window sizes for different types of phrases are different and are determined using a decision tree. Phrases are more important than individual terms. Consequently, documents in response to a query are ranked with matching phrases given a higher priority. We utilize WordNet to disambiguate word senses of query terms. Whenever the sense of a query term is determined, its synonyms, hyponyms, words from its definition and its compound words are considered for possible additions to the query. Experimental results show that our approach yields between 23% and 31% improvements over the best-known results on the TREC 9, 10 and 12 collections for short (title only) queries, without using Web data.