This paper is an attempt to show that an intermediary
level of analysis is an effective way
for c... more This paper is an attempt to show that an intermediary level of analysis is an effective way for carrying out various NLP tasks for linguistically similar languages. We describe a process for developing a simple parser for doing such tasks. This parser uses a grammar driven approach to annotate dependency relations (both inter and intra chunk) at an intermediary level. Ease in identifying a particular dependency relation dictates the degree of analysis reached by the parser. To establish efficiency of the simple parser we show the improvement in its results over previous grammar driven dependency parsing approaches for Indian languages like Hindi. We also propose the possibility of usefulness of the simple parser for Indian languages that are similar in nature.
In this paper, we study the property of
phrasal cohesion for the English-Hindi
language pair. The... more In this paper, we study the property of phrasal cohesion for the English-Hindi language pair. The property of phrasal cohesion states that the linguistic phrases in source language translate as a unit in the target language. The study of phrasal cohesion is important in the context of various applications such as Machine Translation. We compare the degree of phrasal cohesion of English-Hindi and English-French language pairs. We have empirically verified that the degree of phrasal cohesion of English-French language pair is more than the phrasal cohesion of the English-Hindi language pair.
In Transfer-Approach for doing Machine Translation (MT), transfer grammar (TG) is used to transfe... more In Transfer-Approach for doing Machine Translation (MT), transfer grammar (TG) is used to transfer the source language syntactic structure to the target language syntactic structure. TG contains reordering rules that define this transformation. Each rule in TG al-so contains constraints on the source language analysis for the rule to be used. TG is usually created by trained linguists who are aware of structural divergences between the language pair. In this paper, we propose method to au-tomatically induce a TG from a word-aligned parallel corpus. We present methods to gene-ralize rules which can be applied in case rich-er (highly constrained) rules fail. We present the results of our experiments on English-Hindi language pair. Transfer grammar based approaches are more appropriate for languag-es pairs such as English-Hindi as there is large word-order variation between such pairs.
In Transfer-Approach for doing Machine Translation (MT), transfer grammar (TG) is used to transfe... more In Transfer-Approach for doing Machine Translation (MT), transfer grammar (TG) is used to transfer the source language syntactic structure to the target language syntactic structure. TG contains reordering rules that define this transformation. Each rule in TG al-so contains constraints on the source language analysis for the rule to be used. TG is usually created by trained linguists who are aware of structural divergences between the language pair. In this paper, we propose method to automatically induce a TG from a word-aligned parallel corpus. We present methods to generalize rules which can be applied in case rich-er (highly constrained) rules fail. We present the results of our experiments on English-Hindi language pair. Transfer grammar based approaches are more appropriate for languag-es pairs such as English-Hindi as there is large word-order variation between such pairs.
The paper describes an approach to automati-cally annotate a Hindi Treebank using Pani-nian depen... more The paper describes an approach to automati-cally annotate a Hindi Treebank using Pani-nian dependency framework. The annotator is a rule based system and the rules use certain syntactic cues available in a sentence. This au-tomated annotation scheme aims at facilitating manual annotation by reducing time and effort of manual annotators. Also, the aim of auto-matic annotation, among other things, is to in-crease the efficiency of a broad coverage con-straint based Hindi parser. We also evaluate this tool and show its accuracy and coverage.
This paper is an attempt to show that an intermediary
level of analysis is an effective way
for c... more This paper is an attempt to show that an intermediary level of analysis is an effective way for carrying out various NLP tasks for linguistically similar languages. We describe a process for developing a simple parser for doing such tasks. This parser uses a grammar driven approach to annotate dependency relations (both inter and intra chunk) at an intermediary level. Ease in identifying a particular dependency relation dictates the degree of analysis reached by the parser. To establish efficiency of the simple parser we show the improvement in its results over previous grammar driven dependency parsing approaches for Indian languages like Hindi. We also propose the possibility of usefulness of the simple parser for Indian languages that are similar in nature.
In this paper, we study the property of
phrasal cohesion for the English-Hindi
language pair. The... more In this paper, we study the property of phrasal cohesion for the English-Hindi language pair. The property of phrasal cohesion states that the linguistic phrases in source language translate as a unit in the target language. The study of phrasal cohesion is important in the context of various applications such as Machine Translation. We compare the degree of phrasal cohesion of English-Hindi and English-French language pairs. We have empirically verified that the degree of phrasal cohesion of English-French language pair is more than the phrasal cohesion of the English-Hindi language pair.
In Transfer-Approach for doing Machine Translation (MT), transfer grammar (TG) is used to transfe... more In Transfer-Approach for doing Machine Translation (MT), transfer grammar (TG) is used to transfer the source language syntactic structure to the target language syntactic structure. TG contains reordering rules that define this transformation. Each rule in TG al-so contains constraints on the source language analysis for the rule to be used. TG is usually created by trained linguists who are aware of structural divergences between the language pair. In this paper, we propose method to au-tomatically induce a TG from a word-aligned parallel corpus. We present methods to gene-ralize rules which can be applied in case rich-er (highly constrained) rules fail. We present the results of our experiments on English-Hindi language pair. Transfer grammar based approaches are more appropriate for languag-es pairs such as English-Hindi as there is large word-order variation between such pairs.
In Transfer-Approach for doing Machine Translation (MT), transfer grammar (TG) is used to transfe... more In Transfer-Approach for doing Machine Translation (MT), transfer grammar (TG) is used to transfer the source language syntactic structure to the target language syntactic structure. TG contains reordering rules that define this transformation. Each rule in TG al-so contains constraints on the source language analysis for the rule to be used. TG is usually created by trained linguists who are aware of structural divergences between the language pair. In this paper, we propose method to automatically induce a TG from a word-aligned parallel corpus. We present methods to generalize rules which can be applied in case rich-er (highly constrained) rules fail. We present the results of our experiments on English-Hindi language pair. Transfer grammar based approaches are more appropriate for languag-es pairs such as English-Hindi as there is large word-order variation between such pairs.
The paper describes an approach to automati-cally annotate a Hindi Treebank using Pani-nian depen... more The paper describes an approach to automati-cally annotate a Hindi Treebank using Pani-nian dependency framework. The annotator is a rule based system and the rules use certain syntactic cues available in a sentence. This au-tomated annotation scheme aims at facilitating manual annotation by reducing time and effort of manual annotators. Also, the aim of auto-matic annotation, among other things, is to in-crease the efficiency of a broad coverage con-straint based Hindi parser. We also evaluate this tool and show its accuracy and coverage.
Uploads
Papers by Vineet Yadav
level of analysis is an effective way
for carrying out various NLP tasks for linguistically
similar languages. We describe a
process for developing a simple parser for
doing such tasks. This parser uses a grammar
driven approach to annotate dependency relations
(both inter and intra chunk) at an intermediary
level. Ease in identifying a particular
dependency relation dictates the degree of
analysis reached by the parser. To establish efficiency
of the simple parser we show the improvement
in its results over previous grammar
driven dependency parsing approaches for
Indian languages like Hindi. We also propose
the possibility of usefulness of the simple
parser for Indian languages that are similar in nature.
phrasal cohesion for the English-Hindi
language pair. The property of phrasal cohesion
states that the linguistic phrases in
source language translate as a unit in the
target language. The study of phrasal cohesion
is important in the context of various
applications such as Machine Translation.
We compare the degree of phrasal cohesion
of English-Hindi and English-French
language pairs. We have empirically verified
that the degree of phrasal cohesion of
English-French language pair is more than
the phrasal cohesion of the English-Hindi
language pair.
level of analysis is an effective way
for carrying out various NLP tasks for linguistically
similar languages. We describe a
process for developing a simple parser for
doing such tasks. This parser uses a grammar
driven approach to annotate dependency relations
(both inter and intra chunk) at an intermediary
level. Ease in identifying a particular
dependency relation dictates the degree of
analysis reached by the parser. To establish efficiency
of the simple parser we show the improvement
in its results over previous grammar
driven dependency parsing approaches for
Indian languages like Hindi. We also propose
the possibility of usefulness of the simple
parser for Indian languages that are similar in nature.
phrasal cohesion for the English-Hindi
language pair. The property of phrasal cohesion
states that the linguistic phrases in
source language translate as a unit in the
target language. The study of phrasal cohesion
is important in the context of various
applications such as Machine Translation.
We compare the degree of phrasal cohesion
of English-Hindi and English-French
language pairs. We have empirically verified
that the degree of phrasal cohesion of
English-French language pair is more than
the phrasal cohesion of the English-Hindi
language pair.