Searching for authors named "Srinivas Bangalore" – sorted by Relevance.
40 documents found, showing 1 through 10.
Next 10 →
-
unknown title
- …Contemporary multimodal prototypes provide an excellent proof of concept but are not sufficiently robust in their handling of user input to be adopted by real users engaged in complex tasks. The goal of this paper is to investigate techniques that improve the robustness of multimodal understanding t…
- Add To MetaCart
-
Transplanting Supertags from English to Spanish
- …In this paper, we present an approach to quickly develop supertags for a target language given supertags for another language (reference language) , along with a sentence-aligned parallel corpus between reference language and target language pairs. Our method can be interpreted as composing the alig…
- Cited by 1 (1 self) – Add To MetaCart
-
Localizing Dependencies and Supertagging
- … …
- Cited by 1 (0 self) – Add To MetaCart
-
Learning the structure of task-driven human-human dialogs
- …Data-driven techniques have been used for many computational linguistics tasks. Models derived from data are generally more robust than hand-crafted systems since they better reflect the distribution of the phenomena being modeled. With the availability of large corpora of spoken dialog, dialog mana…
- Cited by 5 (1 self) – Add To MetaCart
-
Complexity Of Lexical Descriptions And Its Relevance To Partial Parsing
- …Parsers have proved uncontroversially useful in the domain of processing Programming Languages. However, the issue of parsing, in the domain of Natural Languages, has been a cause for tension between the computational and linguistic perspectives for a long time. In the past, the controversy about na…
- Cited by 6 (1 self) – Add To MetaCart
-
Computing consensus translation from multiple machine translation systems
- …In this paper, we address the problem of computing a consensus translation given the outputs from a set of Machine Translation (MT) systems. The translations from the MT systems are aligned with a multiple string alignment algorithm and the consensus translation is then computed. We describe the mul…
- Cited by 18 (1 self) – Add To MetaCart
-
Bootstrapping Bilingual Data using Consensus Translation for a Multilingual Instant Messaging System
- …One of the primary issues in training statistical translation models is the paucity of bilingual data. In this paper, we propose techniques to alleviate the bilingual data bottleneck by creating a consensus from translations of monolingual data provided by several off-the-shelf translation engines. …
- Cited by 8 (0 self) – Add To MetaCart
-
Knowing a word by the company it keeps using local information in a maximum entropy model for word sense disambiguation
- …Word sense disambiguation (WSD) is a key problem in computational linguistics, with applications in areas such asmachine translation and information retrieval. This paper describes a corpus-based method for word sense disambiguation which usesaversatile maximum entropy technique on simple local lexi…
- Cited by 1 (0 self) – Add To MetaCart
-
Glean: using syntactic information in document filtering
- …In the networked world of the information age, we are exposed to inordinate amounts of information. Search engines and information retrieval systems seek to discern the relevant from the irrelevant information given the context of a user's query. In this paper, we describe a system named Glean, whic…
- Cited by 5 (0 self) – Add To MetaCart
-
Finite-state Methods for Multimodal Parsing and Integration
- …Introduction Finite-state machines have been extensively applied to many aspects of language processing including, speech recognition (Pereira and Riley, 1997; Riccardi et al., 1996), phonology (Kaplan and Kay, 1994; Kartunnen, 1991), morphology (Koskenniemi, 1984), chunking (Abney, 1991; Joshi and…
- Cited by 8 (1 self) – Add To MetaCart
Showing 1 through 10.
Next 10 →
