---
title: "A Semantic Approach to Recognizing Textual Entailment (2005)"
description: "The paper addresses Recognizing Textual Entailment (RTE): deciding whether a hypothesis H… 16 references, cited by 30 papers here."
authors: ["Marta Tatu", "Dan Moldovan"]
year: 2005
venue: "Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/H05-1047/"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/tatu-2005-semantic-approach-recognizing-textual-entailment/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tatu-2005-semantic-approach-recognizing-textual-entailment/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2005](https://md.research.elamur.ai/free/en/papers/2005/) / A Semantic Approach to Recognizing Textual Entailment

# A Semantic Approach to Recognizing Textual Entailment

**Authors:** [Marta Tatu](https://md.research.elamur.ai/free/en/authors/marta-tatu/) and [Dan Moldovan](https://md.research.elamur.ai/free/en/authors/dan-moldovan/) · **Year:** 2005 · **Venue:** [Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/venues/hlt/) ([HLT 2005](https://md.research.elamur.ai/free/en/venues/hlt/2005/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/H05-1047/) · [PDF](https://aclanthology.org/H05-1047.pdf) · [OpenAlex](https://openalex.org/W2079885542)

**Citations:** 80 citations (OpenAlex, 2026-10-14) · [30](https://md.research.elamur.ai/free/en/papers/tatu-2005-semantic-approach-recognizing-textual-entailment/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper addresses Recognizing Textual Entailment (RTE): deciding whether a hypothesis H follows from a text T. The authors argue that semantic parsers recover only part of the relations a sentence expresses, which leaves gaps a logic prover cannot bridge. Their remedy is a "semantic calculus" made of two kinds of axioms. The first kind composes two semantic relations into a new one; for example, KINSHIP is symmetric and transitive. The second kind derives relations between the frame elements of a FrameNet frame.

These axioms are added as an extra module to an existing RTE system that already uses logic forms, WordNet lexical chains, world-knowledge axioms and the COGEX prover. Evaluation on the PASCAL RTE corpus (1367 news pairs) shows accuracy gains of roughly 5 points on test and about 8 points on development. Every application subset improves except Paraphrase Acquisition.

The work matters because it shows that inferring implicit relations makes a system more accurate while lowering its dependence on hand-written world knowledge.

## Key points
- The data is the PASCAL RTE set: 567 development and 800 test (T, H) pairs, balanced 50/50 between true and false entailments. It is split into seven application subsets: IR, CD, RC, QA, IE, MT and PP.
- The pipeline runs in four steps:
  - text is converted to logic form (POS tagging, parsing, NER);
  - a semantic parser adds relations from an inventory of about 40 types (AGT, LOC, KIN, ISA, etc.);
  - the new semantic axioms are applied;
  - COGEX attempts a proof by refutation, relaxing arguments or dropping predicates at a score penalty, and a threshold decides the label.
- Overall accuracy rose from .551 to .604 on test and from .63 to .718 on development. PP slipped slightly, from .45 to .44, and it also had the lowest axiom coverage.
- The axioms fired far more often on texts than on hypotheses (about 13.75% vs 2.87% on test). On their own they resolved 10.25% of true test pairs but only 1.5% of false ones.
- Error analysis found that gains were capped by relations the parser missed. With the axioms in place, the prover also relied much less on world-knowledge axioms.

## Interesting ideas
- Represent relation properties as algebra: when R1(a,b) and R2(b,c) hold, define what follows for (a,c), and mark relations such as KIN as symmetric or transitive. A small, general rule set then recovers facts the text never states directly.
- Attach relation-producing axioms to frames, so that a Departing or Arriving frame yields LOC(Theme, Goal) for each participant. This lets a single frame annotation fan out into explicit facts about every role filler.
- Treat entailment as a matching of relations between analogous concepts. Concepts count as analogous when they are identical or linked through WordNet synonymy, hypernymy or derivation, which avoids word overlap entirely.
- Use graded proof relaxation: when a strict proof fails, loosen arguments and then drop predicates, deducting points for each step, and compare the final score to a threshold.
- Measure how often each rule fires and how often it settles a pair by itself, broken down by data subset and by true/false label. This exposes where the method helps and where it never engages.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (world): A composition table over relation types could let the world-of-the-text layer infer, for instance, that George and Mike are kin, with each derived fact traceable to a named rule.
- **I2** (frames): VerbNet/FrameNet-class rules in prag could turn identified roles into concrete state assertions, such as where each mover ends up, and pass them to the world model.
- **I3** (answer): Answer checking could align question and text graphs edge by edge through WordNet chains, giving an explainable yes/no instead of a similarity score.
- **I4** (answer): Readers could report how much was relaxed to reach an answer, which provides both a confidence value and an explicit list of unmatched pieces.
- **I5** (learn): Per-rule coverage tables split by positive versus negative items would act as a negative control, flagging rules that fire mostly on false cases.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Language Computer](https://md.research.elamur.ai/free/en/companies/language-computer/) — Company, Richardson, United States · 9 works · 1,157 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works

## Cite

Cite as: Marta Tatu and Dan Moldovan. 2005. A Semantic Approach to Recognizing Textual Entailment. Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{tatu2005semantic,
  title = {{A Semantic Approach to Recognizing Textual Entailment}},
  author = {Marta Tatu and Dan Moldovan},
  booktitle = {Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing},
  year = {2005},
  doi = {10.3115/1220575.1220622},
  url = {https://doi.org/10.3115/1220575.1220622}
}
```

- [← previous Arabic Diacritization Using Weighted Finite-State Transducers](https://md.research.elamur.ai/free/en/papers/nelken-2005-arabic-diacritization-weighted-finite-state/)
- [next → Machine Learning for Coreference Resolution: From Local Classification to Global Ranking](https://md.research.elamur.ai/free/en/papers/ng-2005-machine-learning-coreference-resolution-local/)
- [↑ back to papers of 2005](https://md.research.elamur.ai/free/en/papers/2005/)

## References

16 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Collin Baker, Fillmore Charles, and John Love. 1998. [The Berkeley FrameNet project](https://md.research.elamur.ai/free/en/papers/baker-1998-berkeley-framenet/). In Proceedings of COLING/ACL.
2. Samuel Bayer, John Burger, Lisa Ferro, John Henderson, and Alexander Yeh. 2005. MITRE’s Submissions to the EU Pascal RTE Challenge. In Proceedings of the PASCAL RTE Challenge. [find](https://scholar.google.com/scholar?q=Samuel+Bayer%2C+John+Burger%2C+Lisa+Ferro%2C+John+Henderson%2C+and+Alexander+Yeh%2E+2005%2E+MITRE%E2%80%99s+Submissions+to+the+EU+Pascal+RTE+Challenge%2E+In+Proceedings+of+the+PASCAL+RTE+Challenge%2E)
3. Johan Bos and Katja Markert. 2005. Combining Shallow and Deep NLP Methods for Recognizing Textual Entailment. In Proceedings of the PASCAL RTE Challenge. [find](https://scholar.google.com/scholar?q=Johan+Bos+and+Katja+Markert%2E+2005%2E+Combining+Shallow+and+Deep+NLP+Methods+for+Recognizing+Textual+Entailment%2E+In+Proceedings+of+the+PASCAL+RTE+Challenge%2E)
4. Ido Dagan, Oren Glickman, and Bernardo Magnini. 2005. The PASCAL Recognising Textual Entailment Challenge. In Proceedings of the PASCAL RTE Challenge. [find](https://scholar.google.com/scholar?q=Ido+Dagan%2C+Oren+Glickman%2C+and+Bernardo+Magnini%2E+2005%2E+The+PASCAL+Recognising+Textual+Entailment+Challenge%2E+In+Proceedings+of+the+PASCAL+RTE+Challenge%2E)
5. Rodrigo de Salvo Braz, Roxana Girju, Vasin Punyakanok, Dan Roth, and Mark Sammons. 2005. An Inference Model for Semantic Entailment in Natural Language. In Proceedings of the PASCAL RTE Challenge. [find](https://scholar.google.com/scholar?q=Rodrigo+de+Salvo+Braz%2C+Roxana+Girju%2C+Vasin+Punyakanok%2C+Dan+Roth%2C+and+Mark+Sammons%2E+2005%2E+An+Inference+Model+for+Semantic+Entailment+in+Natural+Language%2E+In+Proceedings+of+the+PASCAL+RTE+Challenge%2E)
6. Abraham Fowler, Bob Hauser, Daniel Hodges, Ian Niles, Adrian Novischi, and Jens Stephan. 2005. Applying COGEX to Recognize Textual Entailment. In Proceedings of the PASCAL RTE Challenge. [find](https://scholar.google.com/scholar?q=Abraham+Fowler%2C+Bob+Hauser%2C+Daniel+Hodges%2C+Ian+Niles%2C+Adrian+Novischi%2C+and+Jens+Stephan%2E+2005%2E+Applying+COGEX+to+Recognize+Textual+Entailment%2E+In+Proceedings+of+the+PASCAL+RTE+Challenge%2E)
7. Sanda Harabagiu and Dan Moldovan. 1998. Knowledge Processing on Extended WordNet. In WordNet: an Electronic Lexical Database and Some of its Applications. [find](https://scholar.google.com/scholar?q=Sanda+Harabagiu+and+Dan+Moldovan%2E+1998%2E+Knowledge+Processing+on+Extended+WordNet%2E+In+WordNet%3A+an+Electronic+Lexical+Database+and+Some+of+its+Applications%2E)
8. Jess Herrera, Anselmo Peas, and Felisa Verdejo. 2005. Textual Entailment Recognision Based on Dependency Analysis and WordNet. In Proceedings of the PASCAL RTE Challenge. [find](https://scholar.google.com/scholar?q=Jess+Herrera%2C+Anselmo+Peas%2C+and+Felisa+Verdejo%2E+2005%2E+Textual+Entailment+Recognision+Based+on+Dependency+Analysis+and+WordNet%2E+In+Proceedings+of+the+PASCAL+RTE+Challenge%2E)
9. Valentin Jijkoun and Maarten de Rijke. 2005. Recognizing Textual Entailment Using Lexical Similarity. In Proceedings of the PASCAL RTE Challenge. [find](https://scholar.google.com/scholar?q=Valentin+Jijkoun+and+Maarten+de+Rijke%2E+2005%2E+Recognizing+Textual+Entailment+Using+Lexical+Similarity%2E+In+Proceedings+of+the+PASCAL+RTE+Challenge%2E)
10. Milen Kouylekov and Bernardo Magnini. 2005. Recognizing Textual Entailment with Tree Edit Distance Algorithms. In Proceedings of the PASCAL RTE Challenge. [find](https://scholar.google.com/scholar?q=Milen+Kouylekov+and+Bernardo+Magnini%2E+2005%2E+Recognizing+Textual+Entailment+with+Tree+Edit+Distance+Algorithms%2E+In+Proceedings+of+the+PASCAL+RTE+Challenge%2E)
11. Dan Moldovan and Adrian Novischi. 2002. Lexical Chains for Question Answering. In Proceedings of COLING. [find](https://scholar.google.com/scholar?q=Dan+Moldovan+and+Adrian+Novischi%2E+2002%2E+Lexical+Chains+for+Question+Answering%2E+In+Proceedings+of+COLING%2E)
12. Dan Moldovan and Vasile Rus. 2001. Logic Form Transformation of WordNet and its Applicability to Question Answering. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=Dan+Moldovan+and+Vasile+Rus%2E+2001%2E+Logic+Form+Transformation+of+WordNet+and+its+Applicability+to+Question+Answering%2E+In+Proceedings+of+ACL%2E)
13. Dan Moldovan, Christine Clark, Sanda Harabagiu, and Steve Maiorano. 2003. COGEX A Logic Prover for Question Answering. In Proceedings of the HLT/NAACL. [find](https://scholar.google.com/scholar?q=Dan+Moldovan%2C+Christine+Clark%2C+Sanda+Harabagiu%2C+and+Steve+Maiorano%2E+2003%2E+COGEX+A+Logic+Prover+for+Question+Answering%2E+In+Proceedings+of+the+HLT%2FNAACL%2E)
14. Dan Moldovan, Adriana Badulescu, Marta Tatu, Daniel Antohe, and Roxana Girju. 2004. Models for the Semantic Classification of Noun Phrases. In Proceedings of HLT/NAACL, Computational Lexical Semantics workshop. [find](https://scholar.google.com/scholar?q=Dan+Moldovan%2C+Adriana+Badulescu%2C+Marta+Tatu%2C+Daniel+Antohe%2C+and+Roxana+Girju%2E+2004%2E+Models+for+the+Semantic+Classification+of+Noun+Phrases%2E+In+Proceedings+of+HLT%2FNAACL%2C+Computational+Lexical+Semantics)
15. Eamonn Newman, Nicola Stokes, John Dunnion, and Joe Carthy. 2005. UCD IIRG Approach to the Textual Entailment Challenge. In Proceedings of the PASCAL RTE Challenge. [find](https://scholar.google.com/scholar?q=Eamonn+Newman%2C+Nicola+Stokes%2C+John+Dunnion%2C+and+Joe+Carthy%2E+2005%2E+UCD+IIRG+Approach+to+the+Textual+Entailment+Challenge%2E+In+Proceedings+of+the+PASCAL+RTE+Challenge%2E)
16. Rajat Raina, Aria Haghighi, Christopher Cox, Jenny Finkel, Jeff Michels, Kristina Toutanova, Bill Mac-Cartney, Marie-Catherine de Marneffe, Christopher Manning, and Andrew Ng. 2005. Robust Textual Inference using Diverse Knowledge Sources. In Proceedings of the PASCAL RTE Challenge. [find](https://scholar.google.com/scholar?q=Rajat+Raina%2C+Aria+Haghighi%2C+Christopher+Cox%2C+Jenny+Finkel%2C+Jeff+Michels%2C+Kristina+Toutanova%2C+Bill+Mac%2DCartney%2C+Marie%2DCatherine+de+Marneffe%2C+Christopher+Manning%2C+and+Andrew+Ng%2E+2005%2E+Robust+Textual+Inf)

*Updated 30 October 2026*