---
title: "Automatic Input Enrichment for Selecting Reading Material: An"
description: "Language teachers want reading texts that fit a chosen topic and also contain many examples of the grammar they are teaching. 19 references."
authors: ["Maria Chinkina", "Ankita Oswal", "Detmar Meurers"]
year: 2018
venue: "Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications"
source: "https://aclanthology.org/W18-0504/"
doi: "10.18653/v1/w18-0504"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/chinkina-2018-automatic-input-enrichment-selecting-reading/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/chinkina-2018-automatic-input-enrichment-selecting-reading/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/page/7/) / Automatic Input Enrichment for Selecting Reading Material: An Online Study with English Teachers

# Automatic Input Enrichment for Selecting Reading Material: An Online Study with English Teachers

**Authors:** Maria Chinkina, Ankita Oswal and [Detmar Meurers](https://md.research.elamur.ai/free/en/authors/detmar-meurers/) · **Year:** 2018 · **Venue:** [Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications](https://md.research.elamur.ai/free/en/venues/bea/) ([BEA 2018](https://md.research.elamur.ai/free/en/venues/bea/2018/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/W18-0504/) · [PDF](https://aclanthology.org/W18-0504.pdf) · [DOI 10.18653/v1/w18-0504](https://doi.org/10.18653/v1/w18-0504) · [OpenAlex](https://openalex.org/W2806895290)

**Citations:** 1 citations (OpenAlex, 2026-10-14)

## Summary
Language teachers want reading texts that fit a chosen topic and also contain many examples of the grammar they are teaching. Ordinary search engines match words, not structures, so finding articles rich in a form such as past perfect is hard. The authors evaluate FLAIR, their linguistically aware search tool. It runs on top of Microsoft Bing, detects 87 grammatical forms from the official English curriculum, and re-ranks results so that texts best representing user-selected forms appear first. Because FLAIR draws on Bing's own results, the study measures only the effect of the NLP re-ranking.

In a within-subjects online experiment, English teachers worked through ten topics. For each topic they read one top Bing article and one FLAIR-promoted article, rated each for topical relevance and for how well a given pair of forms was represented, and chose one as a class reading. The study collected 240 responses. Teachers generally preferred FLAIR's texts and rated them significantly higher for form representation. They judged them as relevant to the topic as Bing's. This is empirical support for automated input flood in everyday teaching.

## Key points
- FLAIR combines Microsoft Bing retrieval, third-party text extraction and parsing, detectors for 87 curriculum forms, and a ranking algorithm. Its interface highlights the target forms so teachers can judge complexity and length.
- Each participant read 20 news articles on ten topics, presented in pairs (Bing top result vs. FLAIR choice). The topic and the pair of target forms were held constant within each pair. Article order and the matching of topics to form-pair types were randomized. The tool was a Java J2EE web app, and participants received a 20 Euro voucher.
- There were four hypotheses:
  - H1: teachers prefer FLAIR's texts.
  - H2: FLAIR's texts have richer form representation.
  - H3: FLAIR's texts are less relevant to the topic.
  - H4: rarer forms favour FLAIR more.
  
  H3 was not borne out; relevance came out equivalent.
- Form pairs were grouped as frequent, infrequent or mixed by how often both forms appear in the same document. Examples are can/may (14%), real/unreal conditionals (4%) and past simple/present perfect (63%). Frequent forms gain the least from enrichment.
- Teacher feedback suggested two future directions:
  - offering more varied contexts for each form, via disambiguation of forms and GDEX-style good-example selection;
  - automatically generating exercises on the selected forms.

## Interesting ideas
- Keeping the candidate pool fixed (Bing's results) and changing only the ranking isolates exactly what the linguistic layer adds.
- "Grammar retrieval" treats a syntactic construction, not a keyword, as the search target. This makes parsed analysis the basis for finding documents.
- Classifying form pairs by how often they co-occur in documents predicts where re-ranking actually helps: rare pairs benefit most, frequent ones barely.
- Raters judged two separate axes, content relevance and form representation, before making a forced overall choice, which exposes trade-offs between them.
- The authors propose extending sense disambiguation from words to grammatical forms, e.g., telling apart different uses of a tense.

## For Mova

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

- **I1** (learn): Evaluate a new module by holding upstream candidates constant and swapping only its scoring, so any gain is attributable to that module rather than to retrieval or input differences.
- **I2** (tree): Query parsed UD trees for rare constructions (e.g., unreal conditionals, past perfect) to mine targeted examples for treebank augmentation or parser stress tests.
- **I3** (learn): Stratify evaluation sets by construction rarity, so improvements on rare phenomena are not hidden by averages dominated by frequent forms.
- **I4** (answer): When humans or an LLM teacher assess Mova's answers, score correctness of content and linguistic or explanatory quality separately, then ask for a pairwise preference.
- **I5** (world): Distinguishing tense and aspect uses could sharpen how event order and ongoing states are placed in the world of a text.

*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

- [University of Tübingen](https://md.research.elamur.ai/free/en/universities/university-of-tubingen/) — University, Tübingen, Germany · 78 works · 41,280 citations

📚 Shelves (6): [🖥️ 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 · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Developmental and Educational Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/developmental-and-educational-psychology/) · 523 works

🧭 Topics (1): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,379 works

## Cite

Cite as: Maria Chinkina, Ankita Oswal and Detmar Meurers. 2018. Automatic Input Enrichment for Selecting Reading Material: An Online Study with English Teachers. Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications.

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

```bibtex
@inproceedings{chinkina2018automatic,
  title = {{Automatic Input Enrichment for Selecting Reading Material: An Online Study with English Teachers}},
  author = {Maria Chinkina, Ankita Oswal and Detmar Meurers},
  booktitle = {Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications},
  year = {2018},
  doi = {10.18653/v1/w18-0504},
  url = {https://doi.org/10.18653/v1/w18-0504}
}
```

- [← previous Automatic Identification of Arabic expressions related to future events in Lebanon's economy](https://md.research.elamur.ai/free/en/papers/al-hajj-2018-automatic-identification-arabic-expressions-related/)
- [next → CENTEMENT at SemEval-2018 Task 1: Classification of Tweets using Multiple Thresholds with Self-correction and Weighted Conditional Probabilities](https://md.research.elamur.ai/free/en/papers/ahmad-2018-centement-semeval-2018-task-1/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/7/)

## References

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

1. BT Sue Atkins and Michael Rundell. 2008. The Oxford guide to practical lexicography. Oxford University Press. [find](https://scholar.google.com/scholar?q=BT+Sue+Atkins+and+Michael+Rundell%2E+2008%2E+The+Oxford+guide+to+practical+lexicography%2E+Oxford+University+Press%2E)
2. Stephen Krashen. 1977. Some issues relating to the monitor model. On Tesol, 77(144-158). [find](https://scholar.google.com/scholar?q=Stephen+Krashen%2E+1977%2E+Some+issues+relating+to+the+monitor+model%2E+On+Tesol%2C+77%28144%2D158%29%2E)
3. Lee Becker, Sumit Basu, and Lucy Vanderwende. 2012. Mind the gap: Learning to choose gaps for question generation. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT ’12, pages 742–751, Stroudsburg, PA, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Lee+Becker%2C+Sumit+Basu%2C+and+Lucy+Vanderwende%2E+2012%2E+Mind+the+gap%3A+Learning+to+choose+gaps+for+question+generation%2E+In+Proceedings+of+the+2012+Conference+of+the+North+American+Chapter+of+the+Associatio)
4. Stephen Krashen. 1989. We acquire vocabulary and spelling by reading: Additional evidence for the input hypothesis. The modern language journal, 73(4):440–464. [find](https://scholar.google.com/scholar?q=Stephen+Krashen%2E+1989%2E+We+acquire+vocabulary+and+spelling+by+reading%3A+Additional+evidence+for+the+input+hypothesis%2E+The+modern+language+journal%2C+73%284%29%3A440%E2%80%93464%2E)
5. Jennifer Leeman, Igone Arteagoitia, Boris Fridman, and Catherine Doughty. 1995. Integrating attention to form with meaning: Focus on form in content-based spanish instruction. Attention and awareness in foreign language learning, pages 217–258. [find](https://scholar.google.com/scholar?q=Jennifer+Leeman%2C+Igone+Arteagoitia%2C+Boris+Fridman%2C+and+Catherine+Doughty%2E+1995%2E+Integrating+attention+to+form+with+meaning%3A+Focus+on+form+in+content%2Dbased+spanish+instruction%2E+Attention+and+awareness+)
6. Jasmine Bennöhr. 2007. A web-based personalised textfinder for language learners. In Data Struc-D. I. Slobin, editor. 1985. The crosslinguistic study of language acquisition. L. Erlbaum Associates, Hillsdale, NJ. [find](https://scholar.google.com/scholar?q=Jasmine+Benno%CC%88hr%2E+2007%2E+A+web%2Dbased+personalised+textfinder+for+language+learners%2E+In+Data+Struc%2DD%2E+I%2E+Slobin%2C+editor%2E+1985%2E+The+crosslinguistic+study+of+language+acquisition%2E+L%2E+Erlbaum+Associates%2C+H)
7. Michael H. Long. 1991. Focus on form: A design feature in language teaching methodology. In K. De Bot, C. Kramsch, and R. Ginsberg, editors, Foreign language research in cross-cultural perspective, pages 39–52. John Benjamins, Amsterdam. [find](https://scholar.google.com/scholar?q=Michael+H%2E+Long%2E+1991%2E+Focus+on+form%3A+A+design+feature+in+language+teaching+methodology%2E+In+K%2E+De+Bot%2C+C%2E+Kramsch%2C+and+R%2E+Ginsberg%2C+editors%2C+Foreign+language+research+in+cross%2Dcultural+perspective%2C+pa)
8. Mark Stevenson and Yorick Wilks. 2003. Word-sense disambiguation. In Ruslan Mitkov, editor, The Oxford Handbook of Computational Linguistics, chapter 13, pages 249–265. Oxford University Press. [find](https://scholar.google.com/scholar?q=Mark+Stevenson+and+Yorick+Wilks%2E+2003%2E+Word%2Dsense+disambiguation%2E+In+Ruslan+Mitkov%2C+editor%2C+The+Oxford+Handbook+of+Computational+Linguistics%2C+chapter+13%2C+pages+249%E2%80%93265%2E+Oxford+University+Press%2E)
9. Maria Pigada and Norbert Schmitt. 2006. Vocabulary acquisition from extensive reading: A case study. Reading in a foreign language, 18(1):1. [find](https://scholar.google.com/scholar?q=Maria+Pigada+and+Norbert+Schmitt%2E+2006%2E+Vocabulary+acquisition+from+extensive+reading%3A+A+case+study%2E+Reading+in+a+foreign+language%2C+18%281%29%3A1%2E)
10. Martha Trahey and Lydia White. 1993. Positive evidence and preemption in the second language classroom. Studies in second language acquisition, 15(02):181–204. [find](https://scholar.google.com/scholar?q=Martha+Trahey+and+Lydia+White%2E+1993%2E+Positive+evidence+and+preemption+in+the+second+language+classroom%2E+Studies+in+second+language+acquisition%2C+15%2802%29%3A181%E2%80%93204%2E)
11. Development R Core Team. 2009. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria. [find](https://scholar.google.com/scholar?q=Development+R+Core+Team%2E+2009%2E+R%3A+A+Language+and+Environment+for+Statistical+Computing%2E+R+Foundation+for+Statistical+Computing%2C+Vienna%2C+Austria%2E)
12. Roi Reichart and Ari Rappoport. 2010. Tense sense disambiguation: a new syntactic polysemy task. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 325–334. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Roi+Reichart+and+Ari+Rappoport%2E+2010%2E+Tense+sense+disambiguation%3A+a+new+syntactic+polysemy+task%2E+In+Proceedings+of+the+2010+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+325%E2%80%9333)
13. Sowmya Vajjala and Detmar Meurers. 2012. [On improving the accuracy of readability classification using insights from second language acquisition](https://md.research.elamur.ai/free/en/papers/vajjala-2012-improving-accuracy-readability-classification-insights/). In In Proceedings of the 7th Workshop on Innovative Use of NLP for Building Educational Applications, pages 163–173, Montral, Canada. Association for Computational Linguistics.
14. R. Schmidt. 1990. The role of consciousness in second language learning. Applied Linguistics, 11:206– 226. [find](https://scholar.google.com/scholar?q=R%2E+Schmidt%2E+1990%2E+The+role+of+consciousness+in+second+language+learning%2E+Applied+Linguistics%2C+11%3A206%E2%80%93+226%2E)
15. Bill VanPatten. 1990. Attending to form and content in the input: An experiment in consciousness. Studies in Second Language Acquisition, 12(3):287–301. [find](https://scholar.google.com/scholar?q=Bill+VanPatten%2E+1990%2E+Attending+to+form+and+content+in+the+input%3A+An+experiment+in+consciousness%2E+Studies+in+Second+Language+Acquisition%2C+12%283%29%3A287%E2%80%93301%2E)
16. Donald J Schuirmann. 1987. A comparison of the two one-sided tests procedure and the power approach for assessing the equivalence of average bioavailability. Journal of pharmacokinetics and biopharmaceutics, 15(6):657–680. [find](https://scholar.google.com/scholar?q=Donald+J+Schuirmann%2E+1987%2E+A+comparison+of+the+two+one%2Dsided+tests+procedure+and+the+power+approach+for+assessing+the+equivalence+of+average+bioavailability%2E+Journal+of+pharmacokinetics+and+biopharmac)
17. Bill VanPatten and Soile Oikkenon. 1996. Explanation versus structured input in processing instruction. Studies in Second Language Acquisition, 18(04):495–510. [find](https://scholar.google.com/scholar?q=Bill+VanPatten+and+Soile+Oikkenon%2E+1996%2E+Explanation+versus+structured+input+in+processing+instruction%2E+Studies+in+Second+Language+Acquisition%2C+18%2804%29%3A495%E2%80%93510%2E)
18. Rob Waring and I.S.P. Nation. 2004. Second language reading and incidental vocabulary learning. Angles on the English speaking world, 4:97–110. [find](https://scholar.google.com/scholar?q=Rob+Waring+and+I%2ES%2EP%2E+Nation%2E+2004%2E+Second+language+reading+and+incidental+vocabulary+learning%2E+Angles+on+the+English+speaking+world%2C+4%3A97%E2%80%93110%2E)
19. RJ Senter and Edgar A Smith. 1967. Automated readability index. Technical report, Cincinatti University Ohio. [find](https://scholar.google.com/scholar?q=RJ+Senter+and+Edgar+A+Smith%2E+1967%2E+Automated+readability+index%2E+Technical+report%2C+Cincinatti+University+Ohio%2E)

*Updated 2 November 2026*