Aligning Formal Meaning Representations with Surface Strings for Wide-Coverage Text Generation
نویسندگان
چکیده
Statistical natural language generation from abstract meaning representations presupposes large corpora consisting of text–meaning pairs. Even though such corpora exist nowadays, or could be constructed using robust semantic parsing, the simple alignment between text and meaning representation is too coarse for developing robust (statistical) NLG systems. By reformatting semantic representations as graphs, fine-grained alignment can be obtained. Given a precise alignment at the word level, the complete surface form of a meaning representations can be deduced using a simple declarative rule.
منابع مشابه
Aligning English Strings with Abstract Meaning Representation Graphs
We align pairs of English sentences and corresponding Abstract Meaning Representations (AMR), at the token level. Such alignments will be useful for downstream extraction of semantic interpretation and generation rules. Our method involves linearizing AMR structures and performing symmetrized EM training. We obtain 86.5% and 83.1% alignment F score on development and test sets.
متن کاملAligning Semantic Graphs for Textual Inference and Machine Reading
This paper presents our work on textual inference and situates it within the context of the larger goals of machine reading. The textual inference task is to determine if the meaning of one text can be inferred from the meaning of another and from background knowledge. Our system generates semantic graphs as a representation of the meaning of a text. This paper presents new results for aligning...
متن کاملUnderstanding Descriptions of Visual Scenes Using Graph Grammars
Teaching computers to understand the meaning of natural language text has long been an important goal for Artificial Intelligence. The focus of my work is on the interpretation of descriptions of visual scenes such as ‘A man is sitting on a chair and using the computer’. One application of this research is the automatic generation of 3D scenes (Coyne and Sproat 2001), such as the one in Figure ...
متن کاملCryptic Crossword Clues: Generating Text with a Hidden Meaning
This paper discusses the generation of cryptic crossword clues: a task that involves generating texts that have both a surface reading, based on a natural language interpretation of the words, and a hidden meaning in which the strings that form the text can be interpreted as a puzzle. The process of clue generation realizes a representation of the hidden, puzzle meaning of the clue through the ...
متن کاملAutomatic Alignment of Common Information in Comparable Sentences of Portuguese
The ability to recognize distinct word sequences which refer to the same meaning is of extreme relevance for many applications in NLP, such as automatic summarization, question answering, generation, etc. In this paper we describe our first attempt at aligning common information between portuguese similar sentences. We propose a method based on lexical and syntatic information and some paraphra...
متن کامل