This paper describes an unsupervised strategy to acquire lexico-semantic frames (LSFs) of verbs from sentential parsed corpora (in syntactic level). The problems of acquiring LSFs consist of verb senses ambiguity, diversity of linguistic usages, and lack of completed frame slots in a single sentence. We propose an specific clustering technique based on the Minimum Description Length (MDL) princ...

This paper presents a new method for learning case frames of Japanese polysemous verbs from a roughly parsed corpus when given a semantic hierarchy for nouns (thesaurus). Japanese verbs usually have several meanings which take different case frames. Each contains different types and numbers of case particles (case marker) which turn select different noun categories. The proposed method employs ...

The paper describes the application of kMeans, a standard clustering technique, to the task of inducing semantic classes for German verbs. Using probability distributions over verb subcategorisation frames, we obtained an intuitively plausible clustering of 57 verbs into 14 classes. The automatic clustering was evaluated against independently motivated, handconstructed semantic verb classes. A ...

The issues of recognition of and representation for motion concepts, with all their semantic richness, have been largely ignored by the AI community. However, there are exceptions, such as Miller [1], Abrahamson [2], and in particular, Badler [3]. Badler considered image sequences attempting to provide English descriptions for motions recognized in the images. He provided precise definitions fo...

This paper aims to classify Mandarin verbs of emotion by adopting a frame-based (Fillmore & Atkins 1992) and corpus-based approach, and propose that there should be a more distinct schema than the structure of frames in FrameNet (http://www.icsi.berkeley.edu/ ~FrameNet/). We start with exploring equivalents of the English verbs of the emotion domain in FrameNet, the database provides frame-base...

Parsing plays an important role in semantic role labeling (SRL) because most SRL systems infer semantic relations from 1-best parses. Therefore, parsing errors inevitably lead to labeling mistakes. To alleviate this problem, we propose to use packed forest, which compactly encodes all parses for a sentence. We design an algorithm to exploit exponentially many parses to learn semantic relations ...