http:^^www.cs.utexas.edu^users^ml^nl.html

This data set contains WWW-pages collected from computer science departments of various universities

logic programming (ILP).  ILP, which investigates the learning of
relational (first-order) rules, provides an empirical method for
acquiring knowledge within traditional, symbolic parsing frameworks.<p>

This dissertation details the architecture, implementation and
evaluation of CHILL a computer system for acquiring natural
language parsers by training over corpora of parsed text.  CHILL
treats language acquisition as the learning of search-control rules
within a logic program that implements a shift-reduce parser.  Control
rules are induced using a novel ILP algorithm which handles difficult
issues arising in the induction of search-control heuristics.  Both
the control-rule framework and the induction algorithm are crucial to
CHILL's success.<p>

The main advantage of CHILL over propositional counterparts is
its flexibility in handling varied representations.  CHILL has
produced parsers for various analyses including case-role mapping,
detailed syntactic parse trees, and a logical form suitable for
expressing first-order database queries.  All of these tasks are
accomplished within the same framework, using a single, general
learning method that can acquire new syntactic and semantic categories
for resolving ambiguities.<p>

Experimental evidence from both aritificial and real-world corpora
demonstrate that CHILL learns parsers as well or better than
previous artificial neural network or probablistic approaches on
comparable tasks.  In the database query domain, which goes beyond the
scope of previous empirical approaches, the learned parser outperforms
an existing hand-crafted system.  These results support the claim that
ILP techniques as implemented in CHILL represent a viable
alternative with significant potential advantages over neural-network,
propositional, and probablistic approaches to empirical parser
construction.<p>
</blockquote>

<!WA16><a href="file://ftp.cs.utexas.edu/pub/mooney/papers/chill-dissertation-95.ps.Z">
<!WA17><img align=top src="http://www.cs.utexas.edu/users/ml/paper.xbm"></a><p>


<! ===========================================================================>

<a name="wolfie-ack-95.ps.Z"</a>

<b><li>Acquisition of a Lexicon from Semantic Representations of Sentences<br></b>

Cynthia A. Thompson

<cite>33rd Annual Meeting of the Association of Computational Linguistics</cite>, pp. 335-337, Boston, MA July 1995 (ACL-95). <p>

<blockquote>
A system, WOLFIE, that acquires a mapping of words to their semantic
representation is presented and a preliminary evaluation is performed.
Tree least general generalizations (TLGGs) of the representations of input 
sentences are performed to assist in determining the representations
of individual words in the sentences.  The best guess for a meaning
of a word is the TLGG which overlaps with the highest percentage of 
sentence representations in which that word appears. 
Some promising experimental results on a non-artificial data
set are presented.
</blockquote>

<!WA18><A href="http://www.cs.utexas.edu/users/ml/ftp/papers/wolfie-acl-95.ps.Z">
<!WA19><img align=top src="http://www.cs.utexas.edu/users/ml/paper.xbm"></a><p>

<! ===========================================================================>

<a name="chill-compling-95.ps.Z"</a>

<b><li>An Inductive Logic Programming Method for Corpus-based Parser
Construction<br></b>

John M. Zelle and Raymond J. Mooney<br>

Submitted to Computational Lingusitics<p>

<blockquote>
In recent years there has been considerable research into corpus-based
methods for parser construction.  A common thread in this research has
been the use of propositional representations for learned knowledge.
This paper presents an alternative approach based on techniques from a
subfield of machine learning known as inductive logic programming
(ILP).  ILP, which investigates the learning of relational
(first-order) rules, provides a way of using empricial methods to
acquire knowledge within traditional, symbolic parsing frameworks.  We
describe a novel method for constructing deterministic Prolog parsers
from corpora of parsed sentences.  We also discuss several advantages
of this approach compared to propositional alternatives and present
experimental results on learning complete parsers using several
corpora including the ATIS corpus from the Penn Treebank.
</blockquote>

<!WA20><a href="file://ftp.cs.utexas.edu/pub/mooney/papers/chill-compling-95.ps.Z">
<!WA21><img align=top src="http://www.cs.utexas.edu/users/ml/paper.xbm"></a><p>

<! ===========================================================================>

<a name="chill-ijcai-nll-95.ps.Z"</a>

<b><li>A Comparison of Two Methods Employing Inductive Logic Programming for
Corpus-based Parser Constuction<br></b>

John M. Zelle and Raymond J. Mooney<br>

<cite>Working Notes of the IJCAI-95 Workshop on New Approaches to
Learning for Natural Language Processing</cite>, pp.79-86, Montreal,
Quebec, August, 1995.<p>

<blockquote> 
This paper presents results from recent experiments with CHILL,
a corpus-based parser acquisition system.  CHILL treats grammar
acquisition as the learning of search-control rules within a logic
program.  Unlike many current corpus-based approaches that use
propositional or probabilistic learning algorithms, CHILL uses
techniques from inductive logic programming (ILP) to learn relational
representations.  The reported experiments compare CHILL's
performance to that of a more naive application of ILP to parser
acquisition.  The results show that ILP techniques, as employed in
CHILL, are a viable alternative to propositional methods and
that the control-rule framework is fundamental to CHILL's
success.
</blockquote>

<!WA22><a href="file://ftp.cs.utexas.edu/pub/mooney/papers/chill-ijcai-nll-95.ps.Z">
<!WA23><img align=top src="http://www.cs.utexas.edu/users/ml/paper.xbm"></a><p>

<! ===========================================================================>

<a name="chill-ifoil-ml-95.ps.Z"</a>

<b><li>Inducing Logic Programs without Explicit Negative Examples<br></b>

John M. Zelle, Cynthia A. Thompson, Mary Elaine Califf, and Raymond J. Mooney<br>

<cite>Proceedings of the Fifth International Workshop on Inductive Logic
Programming</cite>, Leuven, Belguim, Sepetember 1995.<p>

<blockquote> This paper presents a method for learning logic programs
without explicit negative examples by exploiting an assumption of
<i>output completeness</i>. A mode declaration is supplied for the
target predicate and each training input is assumed to be accompanied
by all of its legal outputs.  Any other outputs generated by an
incomplete program implicitly represent negative examples; however,
large numbers of ground negative examples never need to be generated.
This method has been incorporated into two ILP systems, CHILLIN and
IFOIL, both of which use intensional background knowledge.  Tests on
two natural language acquisition tasks, case-role mapping and
past-tense learning, illustrate the advantages of the approach.
</blockquote>

<!WA24><a href="file://ftp.cs.utexas.edu/pub/mooney/papers/chill-ifoil-ml-95.ps.Z">
<!WA25><img align=top src="http://www.cs.utexas.edu/users/ml/paper.xbm"></a><p>


<! ===========================================================================>

<a name="foidl-jair-95.ps.Z"</a>

<b><li>Induction of First-Order Decision Lists: Results on Learning the Past Tense of English Verbs<br></b>

Raymond J. Mooney and Mary Elaine Califf <br>

<cite>Journal of Artificial Intelligence Research</cite>, 3 (1995) pp. 1-24.

<blockquote>
This paper presents a method for inducing logic programs from examples that
learns a new class of concepts called first-order decision lists, defined
as ordered lists of clauses each ending in a cut.  The method, called FOIDL, 
is based on FOIL but employs intensional background knowledge and avoids 
the need for explicit negative examples.  It is particularly useful for 
problems that involve rules with specific exceptions, such as learning the 
past-tense of English verbs, a task widely studied in the context of the 
symbolic/connectionist debate.  FOIDL is able to learn concise, accurate 
programs for this problem from significantly fewer examples than previous 
methods (both connectionist and symbolic).
</blockquote>

<!WA26><a href="file://ftp.cs.utexas.edu/pub/mooney/papers/foidl-jair-95.ps.Z">
<!WA27><img align=top src="http://www.cs.utexas.edu/users/ml/paper.xbm"></a><p>

<! ===========================================================================>

<a name="chill-aaai-94.ps.Z" </a>

<b> <li> Inducing Deterministic Prolog Parsers From Treebanks:
A Machine Learning Approach </b> <br>  

John M. Zelle and Raymond J. Mooney <br> 

<cite> Proceedings of the Twelfth National Conference on
AI</cite>, pp. 748-753, Seattle, WA, July 1994. (AAAI-94) <p>
 
<blockquote>
This paper presents a method for constructing deterministic, context-sensitive,
Prolog parsers from corpora of parsed sentences. Our approach uses recent
machine learning methods for inducing Prolog rules from examples (inductive
logic programming).  We discuss several advantages of this method compared to
recent statistical methods and present results on learning complete parsers
from portions of the ATIS corpus.
</blockquote>

<!WA28><a href="file://ftp.cs.utexas.edu/pub/mooney/papers/chill-aaai-94.ps.Z">
<!WA29><img align=top src="http://www.cs.utexas.edu/users/ml/paper.xbm"></a><p>

<! ===========================================================================>

<a name="dolphin-chill-proposal-93.ps.Z" </a>

<b> <li> Learning Search-Control Heuristics for Logic Programs:
Applications to Speedup Learning and Language Acquisition </b> <br>

John M. Zelle <br> 

Ph.D. proposal, Department of Computer Sciences, University of Texas
at Austin, 1993. <p>

<blockquote> 
This paper presents a general framework, learning
search-control heuristics for logic programs, which can be used to
improve both the efficiency and accuracy of knowledge-based systems
expressed as definite-clause logic programs.  The approach combines
techniques of explanation-based learning and recent advances in
inductive logic programming to learn clause-selection heuristics that
guide program execution.  Two specific applications of this framework
are detailed: dynamic optimization of Prolog programs (improving
efficiency) and natural language acquisition (improving accuracy).  In
the area of program optimization, a prototype system, DOLPHIN, is able
to transform some intractable specifications into polynomial-time
algorithms, and outperforms competing approaches in several benchmark
speedup domains.  A prototype language acquisition system, CHILL, is
also described.  It is capable of automatically acquiring semantic
grammars, which uniformly incorprate syntactic and semantic
constraints to parse sentences into case-role representations.
Initial experiments show that this approach is able to construct
accurate parsers which generalize well to novel sentences and
significantly outperform previous approaches to learning case-role
mapping based on connectionist techniques.  Planned extensions of the
general framework and the specific applications as well as plans for
further evaluation are also discussed.  
</blockquote>

<!WA30><a href="file://ftp.cs.utexas.edu/pub/mooney/papers/dolphin-chill-proposal-93.ps.Z">
<!WA31><img align=top src="http://www.cs.utexas.edu/users/ml/paper.xbm"></a><p>

<! ===========================================================================>

<a name="chill-aaai-93.ps.Z" </a>

<b> <li> Learning Semantic Grammars With Constructive Inductive Logic Programming </b> <br> 

John M. Zelle  and Raymond J. Mooney <br> 

<cite> Proceedings of the Eleventh National Conference of the American
Association for Artificial Intelligence</cite>, pp. 817-822,
Washington, D.C. July 1993 (AAAI-93). <p>

<blockquote>
Automating the construction of semantic grammars is a difficult and
interesting problem for machine learning.  This paper shows how the
semantic-grammar acquisition problem can be viewed as the learning of
search-control heuristics in a logic program.  Appropriate control
rules are learned using a new first-order induction algorithm that
automatically invents useful syntactic and semantic categories.
Empirical results show that the learned parsers generalize well to
novel sentences and out-perform previous approaches based on
connectionist techniques.
</blockquote>

<!WA32><a href="file://ftp.cs.utexas.edu/pub/mooney/papers/chill-aaai-93.ps.Z">
<!WA33><img align=top src="http://www.cs.utexas.edu/users/ml/paper.xbm"></a><p>


<! ===========================================================================>

<hr>
<address><!WA34><a href="http://www.cs.utexas.edu/users/estlin/">[e-mail]</a></address>