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.

Visual Grounding via Accumulated Attention

Abstract: Visual Grounding (VG) aims to locate the most relevant object or region in an image, based on a natural language query. The query can be a phrase, a sentence or even a multi-round dialogue. There are three main challenges in VG: 1) what is the main focus in a query; 2) how to understand an image; 3) how to locate an object. Most existing methods combine all the information curtly, which may suffer from the problem of information redundancy (i.e. ambiguous query, complicated image and a large number of objects). In this paper, we formulate these challenges as three attention problems and propose an accumulated attention (A-ATT) mechanism to reason among them jointly. Our A-ATT mechanism can circularly accumulate the attention for useful information in image, query, and objects, while the noises are ignored gradually. We evaluate the performance of A-ATT on four popular datasets (namely Refer-COCO, ReferCOCO+, ReferCOCOg, and Guesswhat?!), and the experimental results show the superiority of the proposed method in term of accuracy.

System and method for natural language parsing by initiating processing prior to entry of complete sentences

Abstract: A system and method for parsing natural language is provided. The system comprises a plurality of computer program code modules which address a plurality of predetermined lookup tables. Strings of characters, such as words, assigned one or more syntactical tags identifying the grammatical roles the strings can play are stored in a dictionary and retrieved as a system user inputs text to be processed. The tags are manipulated by a phrase parsing program module and translated into phrases according to grammatical rules stored in a lookup table. Sequences of the phrases corresponding to input sentences are maniplated by a sentence checking program module which consults another suitable rule table. The system and method optionally provide help in identifying grammatically incorrect passages in the input text.

German Children’s Comprehension of Word Order and Case Marking in Causative Sentences

Abstract: Two comprehension experiments were conducted to investigate whether German children are able to use the grammatical cues of word order and word endings (case markers) to identify agents and patients in a causative sentence and whether they weigh these two cues differently across development. Two-year-olds correctly understood only sentences with both cues supporting each other--the prototypical form. Five-year-olds were able to use word order by itself but not case markers. Only 7-year-olds behaved like adults by relying on case markers over word order when the two cues conflicted. These findings suggest that prototypical instances of linguistic constructions with redundant grammatical marking play a special role in early acquisition, and only later do children isolate and weigh individual grammatical cues appropriately.

Tracking time using portable recorders and speech recognition

Abstract: In general, the present invention converts speech, preferably recorded on a portable recorder, to text, analyzes the text, and determines voice commands and times when the voice commands occurred. Task names are associated with voice commands and time segments. These time segments and tasks may be packaged as time increments and stored (e.g., in a file or database) for further processing. Preferably, phrase grammar rules are used when analyzing the text, as this helps to determine voice commands. Using phrase grammar rules also allows the text to contain a variety of topics, only some of which are pertinent to tracking time.

Contextual Phrase-Level Polarity Analysis Using Lexical Affect Scoring and Syntactic N-Grams

Abstract: We present a classifier to predict contextual polarity of subjective phrases in a sentence. Our approach features lexical scoring derived from the Dictionary of Affect in Language (DAL) and extended through WordNet, allowing us to automatically score the vast majority of words in our input avoiding the need for manual labeling. We augment lexical scoring with n-gram analysis to capture the effect of context. We combine DAL scores with syntactic constituents and then extract n-grams of constituents from all sentences. We also use the polarity of all syntactic constituents within the sentence as features. Our results show significant improvement over a majority class baseline as well as a more difficult baseline consisting of lexical n-grams.