Topic
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.
Papers published on a yearly basis
Papers
More filters
01 Nov 2019
TL;DR: A generic evaluation framework, Perturbation Sensitivity Analysis, is proposed, which detects unintended model biases related to named entities, and requires no new annotations or corpora to be employed.
Abstract: Data-driven statistical Natural Language Processing (NLP) techniques leverage large amounts of language data to build models that can understand language. However, most language data reflect the public discourse at the time the data was produced, and hence NLP models are susceptible to learning incidental associations around named referents at a particular point in time, in addition to general linguistic meaning. An NLP system designed to model notions such as sentiment and toxicity should ideally produce scores that are independent of the identity of such entities mentioned in text and their social associations. For example, in a general purpose sentiment analysis system, a phrase such as I hate Katy Perry should be interpreted as having the same sentiment as I hate Taylor Swift. Based on this idea, we propose a generic evaluation framework, Perturbation Sensitivity Analysis, which detects unintended model biases related to named entities, and requires no new annotations or corpora. We demonstrate the utility of this analysis by employing it on two different NLP models — a sentiment model and a toxicity model — applied on online comments in English language from four different genres.
94 citations
TL;DR: In both experiments, naming latencies decreased with increasing frequency of the multi-word phrase, and were unaffected by the frequency ofThe object name in the utterance.
Abstract: A classic debate in the psychology of language concerns the question of the grain-size of the linguistic information that is stored in memory. One view is that only morphologically simple forms are stored (e.g., ‘car’, ‘red’), and that more complex forms of language such as multi-word phrases (e.g., ‘red car’) are generated on-line from the simple forms. In two experiments we tested this view. In Experiment 1, participants produced noun+adjective and noun+noun phrases that were elicited by experimental displays consisting of colored line drawings and two superimposed line drawings. In Experiment 2, participants produced noun+adjective and determiner+noun+adjective utterances elicited by colored line drawings. In both experiments, naming latencies decreased with increasing frequency of the multi-word phrase, and were unaffected by the frequency of the object name in the utterance. These results suggest that the language system is sensitive to the distribution of linguistic information at grain-sizes beyond individual words.
94 citations
TL;DR: In this article, the authors argue that the definite article cannot occur when a possessive phrase is present in the NP (e.g. English *the my book, *John's the book).
Abstract: In many languages the definite article cannot occur when a possessive phrase is present in the NP (e.g. English *the my book, *John's the book). I argue that these patterns can be understood in terms of economic motivation because possessed NPs are very likely to be definite. A structural explanation in terms of a unique determiner position is insufficient to account for the full range of attested crosslinguistic patterns, and the universal generalizations that do seem to be valid can be derived from the economy-based explanation. Finally I show how the performance motivation of economy creates the competence pattern in diachronic change
94 citations
TL;DR: In this paper, it was shown that the postion of inflected verbs in early Yiddish varies between second position and positions later in the clause, and that the phrase structure changed from infl-final to infl-medial.
Abstract: The postion of inflected verbs in early Yiddish varies between second position and positions later in the clause. Standard distributional tests establish that this reflects variation in the underlying position of infl, and that Yiddish phrase structure changed from infl-final to infl-medial. Based on clauses containing the relevant structural diagnostics, we can estimate the rate of this change. We cannot, however, determine the phrase structure of structurally ambiguous clauses (i.e., those superficially consistent with either of the phrase structures) with certainty. Nevertheless, we can use quantitative methods to estimate the likelihood of such clauses being infl-medial, and we can then use these likelihoods to provide an additional estimate of the rate of the change. Comparing both estimates reveals that they do not differ significantly. The implications of this result are briefly examined in conclusion.
94 citations
03 May 1982
TL;DR: A real time text-to-speech conversion system has been developed that converts ordinary English spelling and/or simple numerical and algebraic expressions to speech by a synthesis-by-rule program and formant synthesizer.
Abstract: A real time text-to-speech conversion system has been developed. Input is ordinary English spelling and/or simple numerical and algebraic expressions. Dynamic selection between a male or female output voice is under user control. The system executes a set of about 500 letter-to-sound rules to guess at the pronunciation of words that do not match a carefully selected exceptions dictionary of about 1500 words. A very simple syntactic analyzer determines probable locations of phrase and clause boundaries in order to improve the naturalness and intelligibility of input sentences. The resulting phonemic representation is converted to speech by a synthesis-by-rule program and formant synthesizer. The rule program differs from others of this type in having an extensive set of segment duration rules and many detailed rules for the synthesis of consonant-vowel transitions.
94 citations