Identifying Synonyms among Distributionally Similar Words
نویسندگان
چکیده
We have developed a simulation model that accepts instructions in unconstrained natural language, and then guides a robot to the correct destination. The instructions are segmented on the basis of the actions to be taken, and each segment is labeled with the required action. This flat formulation reduces the problem to a sequential labeling task, to which machine learning methods are applied. We propose an innovative machine learning method for explicitly modeling the actions described in instructions and integrating learning and inference about the physical environment. We obtained a corpus of 840 route instructions that experimenters verified as follow-able, given by people in building navigation situations. Using the four-fold cross validation, our experiments showed that the simulated robot reached the correct destination 88% of the time.
منابع مشابه
Using Mined Coreference Chains as a Resource for a Semantic Task
•Motivation: use output of coreference resolution system as a resource for semantic tasks •Coreference chains: complementary properties compared to other resources, such as cooccurrence statistics , e.g.: “cows” “cattle” vs. “cows” “milk” •Coreference-based similarity can be used as an additional feature for any task that distributional similarity is useful for (e.g. finding alternative names f...
متن کاملVisual synonyms for landmark image retrieval
1077-3142/$ see front matter 2011 Elsevier Inc. A doi:10.1016/j.cviu.2011.10.004 ⇑ Corresponding author. E-mail address: [email protected] (E. Gavves). In this paper, we address the incoherence problem of the visual words in bag-of-words vocabularies. Different from existing work, which assigns words based on closeness in descriptor space, we focus on identifying pairs of independent, distant word...
متن کاملSemantic Word Clusters Using Signed Spectral Clustering
Vector space representations of words capture many aspects of word similarity, but such methods tend to produce vector spaces in which antonyms (as well as synonyms) are close to each other. For spectral clustering using such word embeddings, words are points in a vector space where synonyms are linked with positive weights, while antonyms are linked with negative weights. We present a new sign...
متن کاملSemantic Word Clusters Using Signed Normalized Graph Cuts
Vector space representations of words capture many aspects of word similarity, but such methods tend to make vector spaces in which antonyms (as well as synonyms) are close to each other. We present a new signed spectral normalized graph cut algorithm, signed clustering, that overlays existing thesauri upon distributionally derived vector representations of words, so that antonym relationships ...
متن کاملContextual Characteristics of Concrete and Abstract Words
In this work we investigate commonalities and differences between the semantic representations of concrete and abstract words using human judgments and distributional semantics. We tackle the following questions: a) Does distributional similarity imply similarity in concreteness vs. abstractness? b) How do concrete and abstract context words co-occur with concrete and abstract words? c) Are our...
متن کامل